{
  "fixes": {
    "slug": "google-sheets-api",
    "name": "Google Sheets API",
    "listing": "https://www.anchorterminal.com/tools/google-sheets-api",
    "markdown": "# Fix list: Google Sheets API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/google-sheets-api, the October 2026 research run, assessed 8 October 2026. Grade BB, 76.3 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Google Sheets API: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Payments \u0026 pricing, 35 out of 100, up to 8.1 more on the total\n\nWhy it scored 35: No x402, MPP or L402 (0). Standard use is free within published quotas, but the charge for exceeding them, planned for later in 2026, has no published price (15 of 20). No charge and no card needed to enable the API (20). A person creates a Cloud project and an OAuth consent screen and grants consent, and the MCP server needs Developer Preview Programme enrolment (0). Total 35.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 2. Agent ergonomics, 74 out of 100, up to 4.2 more on the total\n\nWhy it scored 74: Responses size with A1 ranges, a fields mask and includeGridData off by default. The MCP server has six tools, but its tools/list response measured 39 KB on 8 October, 24 KB of it one tool description (22 of 25). batchGet, data filters on developer metadata and majorDimension, but no paging and no row filter or query on values (14 of 20). Standard Google error bodies with a status and message, thinly documented for Sheets (12 of 20). values.update is safe to repeat and batches are atomic, but there is no idempotency key for values.append. The MCP tools carry annotations, with readOnlyHint true on the two read tools, though update_spreadsheet is marked destructiveHint false while its request list includes deleteSheet, deleteDimension and deleteRange (12 of 20). Google API client libraries for Go, Java, Node.js, Python and others, and few required parameters beyond valueInputOption on writes (14 of 15). Total 74.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 3. Security \u0026 auth, 80 out of 100, up to 3.5 more on the total\n\nWhy it scored 80: OAuth 2.0 with five scopes, short-lived revocable tokens and a per-file drive.file scope (30), less 10 because the discovery document lists access_token, oauth_token and key as URL query parameters and Google's system parameters page documents key in the query string (20). spreadsheets.readonly for reading and drive.file for per-file access, but scopes can't be limited to one sheet, nothing confirms a delete, and the MCP update_spreadsheet tool is annotated as not destructive (16 of 20). The MCP setup page warns about indirect prompt injection and requires screening with Model Armor or a documented alternative (12 of 15). Drive log events record API access to files as Item content accessed, with the OAuth client ID and API method, for Workspace admins only; no per-call log for personal accounts was found (12 of 15). security.txt valid to 1 April 2030, Google's vulnerability reward programme, and Google's SOC 2 page lists Google Sheets among the Workspace services in the quarterly Type II reports (20). Total 80.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 4. Schema \u0026 documentation, 83 out of 100, up to 2.8 more on the total\n\nWhy it scored 83: Google publishes a discovery document, not OpenAPI, which is a machine-readable contract all the same, at revision 20260930 with 17 methods and 273 schemas (25). llms.txt returned 404 at developers.google.com, /workspace and /workspace/sheets on 8 October, but doc pages return Markdown when .md.txt is appended to the URL; we found no index or link that advertises it (5 of 10). Reference pages say what each method does, and the MCP tool descriptions map each tool to its REST method, but few say when not to call (15 of 20). Typed parameters with enums such as ValueInputOption, ValueRenderOption and Dimension; the MCP update_spreadsheet tool takes its requests as untyped objects (13 of 15). Code samples in several languages across the guides, but error documentation is thin, a troubleshooting page for 400, 500 and 503 and an ErrorCode enum with three values (10 of 15). v4 in the path and dated release notes with a feed (15). Total 83.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 5. Reliability, 90 out of 100, up to 2 more on the total\n\nWhy it scored 90: Graded on the REST API, which is the generally available surface. The Google Workspace Status Dashboard lists Sheets with an incidents feed that ran from 9 October 2025 to 25 September 2026 when read on 8 October (20). The feed's only Sheets incident is 12 November 2025, 4 hours 45 minutes with Docs, Forms and Slides, so the 90 days to 8 October are clean. The dashboard tracks the Sheets product, not the API alone (30). 300 reads and 300 writes a minute per project and 60 each per user (15). The limits page gives a truncated exponential backoff formula for 429 and the troubleshooting page covers 503, and batch updates apply atomically, but there is no idempotency key or retry guidance for values.append (10 of 15). The Workspace SLA names Google Sheets at 99.9 per cent but measures Downtime in the user web interface and doesn't name the API (5 of 10). The REST API is GA; the MCP server is a Developer Preview and isn't the surface graded here (10). Total 90.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 6. Transparency \u0026 trust, 80 out of 100, up to 1.8 more on the total\n\nMade of editorial 65, provenance 94.\n\nWhy it scored 80: Closed service under the Google APIs Terms of Service, last modified 9 November 2021, with Apache-2.0 client libraries (15 of 30). The Google privacy policy (effective 1 October 2026) covers end users, the Cloud Data Processing Addendum sets deletion within a maximum of 180 days for Workspace customers, and the API Services User Data Policy limits what apps may do with user data. We found no retention statement specific to Sheets API data (18 of 30). Dated notices in the release notes, such as the v3 turndown on 2 August 2021, and 90 days' notice promised before quota charges, but no stated deprecation period, and the API terms let Google discontinue an API at any time (12 of 20). The Workspace subprocessor list, last modified 23 July 2026, gives each third party's activity and processing countries for all Workspace Core Services. It covers Workspace customers, not personal accounts (20). Total 65.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Terms of service: read, states 6 of the 7 things a reader expects, and has 1 clause that costs points (7.1 of 10)\n- Privacy policy: read, states 7 of the 8 things a reader expects, and has 1 clause that costs points (7.3 of 10)\n\n## 7. Maintenance \u0026 community, 85 out of 100, up to 1.3 more on the total\n\nWhy it scored 85: @googleapis/sheets 18.1.1 on 7 October 2026 and release notes on 1 October 2026 (30). Release notes on 13 July, 23 July, 30 September and 1 October 2026, all within 90 days (20). Dated release notes with a feed, a public issue tracker, a developer forum and a Stack Overflow tag; we didn't sample replies (12 of 15). Current official client libraries, with google-api-python-client 2.201.0 on 30 September 2026 (15). Clients regenerate from discovery, the Node package moved to a Node 22 minimum through four breaking majors in September 2026, and we didn't check the CI pass state (8 of 10). Total 85.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- Google hasn't said when quota overage charges start or what they cost; the Workspace model page promises 90 days' notice\n- The Workspace SLA measures Downtime in the user web interface; whether failures of the Sheets API alone count isn't stated\n- Whether the Markdown copies at .md.txt URLs are a supported interface isn't stated; no page we read links to them\n- unchecked: replies on Google's public issue tracker for the Sheets API\n- unchecked: the CI pass state of google-api-nodejs-client and google-api-python-client\n- unchecked: Workspace data regions for Sheets, the help page we tried returned 404\n- unchecked: the SOC 2 reports themselves, which sit behind Compliance Reports Manager; we read only the public page that lists Google Sheets\n- pypiWeekly is for google-api-python-client, which serves every Google API, not Sheets alone\n\n## Weaknesses\n\n- Quotas are 300 reads and 300 writes a minute per project and 60 each per user per project\n- No row filter, query or paging on reads. An agent asks for A1 ranges and trims with a fields mask\n- No idempotency key, so a values.append retried after the 180-second timeout can add the rows twice\n- The MCP server is Developer Preview, and its update_spreadsheet tool carries destructiveHint false although it can delete sheets, rows and ranges\n- Scopes apply to a whole spreadsheet file, not one sheet, and overage charges planned for later in 2026 have no published price\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Ask for drive.file where the user picks the files. spreadsheets and spreadsheets.readonly are sensitive scopes and need extra verification for a public app\n- Send valueInputOption=USER_ENTERED to write formulas. With RAW the string =1+2 is stored as text\n- Put related changes in one spreadsheets.batchUpdate. It counts as one write request and none of it applies if any request is invalid\n- Pass ranges and a fields mask on spreadsheets.get and leave includeGridData off for large files\n- Back off exponentially on 429 and 503, and keep to one request a second per spreadsheet. After a timeout on values.append, read the range before retrying\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "BB",
    "score": 76.3,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 35,
        "maxGain": 8.1,
        "reason": "No x402, MPP or L402 (0). Standard use is free within published quotas, but the charge for exceeding them, planned for later in 2026, has no published price (15 of 20). No charge and no card needed to enable the API (20). A person creates a Cloud project and an OAuth consent screen and grants consent, and the MCP server needs Developer Preview Programme enrolment (0). Total 35.",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 74,
        "maxGain": 4.2,
        "reason": "Responses size with A1 ranges, a fields mask and includeGridData off by default. The MCP server has six tools, but its tools/list response measured 39 KB on 8 October, 24 KB of it one tool description (22 of 25). batchGet, data filters on developer metadata and majorDimension, but no paging and no row filter or query on values (14 of 20). Standard Google error bodies with a status and message, thinly documented for Sheets (12 of 20). values.update is safe to repeat and batches are atomic, but there is no idempotency key for values.append. The MCP tools carry annotations, with readOnlyHint true on the two read tools, though update_spreadsheet is marked destructiveHint false while its request list includes deleteSheet, deleteDimension and deleteRange (12 of 20). Google API client libraries for Go, Java, Node.js, Python and others, and few required parameters beyond valueInputOption on writes (14 of 15). Total 74.",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 80,
        "maxGain": 3.5,
        "reason": "OAuth 2.0 with five scopes, short-lived revocable tokens and a per-file drive.file scope (30), less 10 because the discovery document lists access_token, oauth_token and key as URL query parameters and Google's system parameters page documents key in the query string (20). spreadsheets.readonly for reading and drive.file for per-file access, but scopes can't be limited to one sheet, nothing confirms a delete, and the MCP update_spreadsheet tool is annotated as not destructive (16 of 20). The MCP setup page warns about indirect prompt injection and requires screening with Model Armor or a documented alternative (12 of 15). Drive log events record API access to files as Item content accessed, with the OAuth client ID and API method, for Workspace admins only; no per-call log for personal accounts was found (12 of 15). security.txt valid to 1 April 2030, Google's vulnerability reward programme, and Google's SOC 2 page lists Google Sheets among the Workspace services in the quarterly Type II reports (20). Total 80.",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 83,
        "maxGain": 2.8,
        "reason": "Google publishes a discovery document, not OpenAPI, which is a machine-readable contract all the same, at revision 20260930 with 17 methods and 273 schemas (25). llms.txt returned 404 at developers.google.com, /workspace and /workspace/sheets on 8 October, but doc pages return Markdown when .md.txt is appended to the URL; we found no index or link that advertises it (5 of 10). Reference pages say what each method does, and the MCP tool descriptions map each tool to its REST method, but few say when not to call (15 of 20). Typed parameters with enums such as ValueInputOption, ValueRenderOption and Dimension; the MCP update_spreadsheet tool takes its requests as untyped objects (13 of 15). Code samples in several languages across the guides, but error documentation is thin, a troubleshooting page for 400, 500 and 503 and an ErrorCode enum with three values (10 of 15). v4 in the path and dated release notes with a feed (15). Total 83.",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 90,
        "maxGain": 2,
        "reason": "Graded on the REST API, which is the generally available surface. The Google Workspace Status Dashboard lists Sheets with an incidents feed that ran from 9 October 2025 to 25 September 2026 when read on 8 October (20). The feed's only Sheets incident is 12 November 2025, 4 hours 45 minutes with Docs, Forms and Slides, so the 90 days to 8 October are clean. The dashboard tracks the Sheets product, not the API alone (30). 300 reads and 300 writes a minute per project and 60 each per user (15). The limits page gives a truncated exponential backoff formula for 429 and the troubleshooting page covers 503, and batch updates apply atomically, but there is no idempotency key or retry guidance for values.append (10 of 15). The Workspace SLA names Google Sheets at 99.9 per cent but measures Downtime in the user web interface and doesn't name the API (5 of 10). The REST API is GA; the MCP server is a Developer Preview and isn't the surface graded here (10). Total 90.",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 80,
        "maxGain": 1.8,
        "reason": "Closed service under the Google APIs Terms of Service, last modified 9 November 2021, with Apache-2.0 client libraries (15 of 30). The Google privacy policy (effective 1 October 2026) covers end users, the Cloud Data Processing Addendum sets deletion within a maximum of 180 days for Workspace customers, and the API Services User Data Policy limits what apps may do with user data. We found no retention statement specific to Sheets API data (18 of 30). Dated notices in the release notes, such as the v3 turndown on 2 August 2021, and 90 days' notice promised before quota charges, but no stated deprecation period, and the API terms let Google discontinue an API at any time (12 of 20). The Workspace subprocessor list, last modified 23 July 2026, gives each third party's activity and processing countries for all Workspace Core Services. It covers Workspace customers, not personal accounts (20). Total 65.",
        "blend": "editorial 65, provenance 94",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 85,
        "maxGain": 1.3,
        "reason": "@googleapis/sheets 18.1.1 on 7 October 2026 and release notes on 1 October 2026 (30). Release notes on 13 July, 23 July, 30 September and 1 October 2026, all within 90 days (20). Dated release notes with a feed, a public issue tracker, a developer forum and a Stack Overflow tag; we didn't sample replies (12 of 15). Current official client libraries, with google-api-python-client 2.201.0 on 30 September 2026 (15). Clients regenerate from discovery, the Node package moved to a Node 22 minimum through four breaking majors in September 2026, and we didn't check the CI pass state (8 of 10). Total 85.",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      }
    ],
    "provenance": [
      {
        "label": "Terms of service",
        "value": "read, states 6 of the 7 things a reader expects, and has 1 clause that costs points",
        "points": 7.1,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 7 of the 8 things a reader expects, and has 1 clause that costs points",
        "points": 7.3,
        "max": 10
      }
    ],
    "unchecked": [
      "Google hasn't said when quota overage charges start or what they cost; the Workspace model page promises 90 days' notice",
      "The Workspace SLA measures Downtime in the user web interface; whether failures of the Sheets API alone count isn't stated",
      "Whether the Markdown copies at .md.txt URLs are a supported interface isn't stated; no page we read links to them",
      "unchecked: replies on Google's public issue tracker for the Sheets API",
      "unchecked: the CI pass state of google-api-nodejs-client and google-api-python-client",
      "unchecked: Workspace data regions for Sheets, the help page we tried returned 404",
      "unchecked: the SOC 2 reports themselves, which sit behind Compliance Reports Manager; we read only the public page that lists Google Sheets",
      "pypiWeekly is for google-api-python-client, which serves every Google API, not Sheets alone"
    ],
    "weaknesses": [
      "Quotas are 300 reads and 300 writes a minute per project and 60 each per user per project",
      "No row filter, query or paging on reads. An agent asks for A1 ranges and trims with a fields mask",
      "No idempotency key, so a values.append retried after the 180-second timeout can add the rows twice",
      "The MCP server is Developer Preview, and its update_spreadsheet tool carries destructiveHint false although it can delete sheets, rows and ranges",
      "Scopes apply to a whole spreadsheet file, not one sheet, and overage charges planned for later in 2026 have no published price"
    ],
    "agentNotes": [
      "Ask for drive.file where the user picks the files. spreadsheets and spreadsheets.readonly are sensitive scopes and need extra verification for a public app",
      "Send valueInputOption=USER_ENTERED to write formulas. With RAW the string =1+2 is stored as text",
      "Put related changes in one spreadsheets.batchUpdate. It counts as one write request and none of it applies if any request is invalid",
      "Pass ranges and a fields mask on spreadsheets.get and leave includeGridData off for large files",
      "Back off exponentially on 429 and 503, and keep to one request a second per spreadsheet. After a timeout on values.append, read the range before retrying"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}