# Fix list: Google Calendar API From Anchor Terminal's listing at https://www.anchorterminal.com/tools/google-calendar-api, the October 2026 research run, assessed 1 October 2026. Grade A, 79.5 out of 100. This 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. For a coding agent working on Google Calendar 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. ## 1. Payments & pricing, 35 out of 100, up to 8.1 more on the total Why it scored 35: No x402, MPP or L402 (0). Free within published quotas, but the price for use above 1,000,000 requests a day, planned for later in 2026, isn't published yet (15). No charge for standard use and no card needed to enable the API (20). A person creates a Cloud project, an OAuth consent screen and, for restricted scopes, goes through app verification (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments): 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. - 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. - 20, a free tier or trial that doesn't need a card. - 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. ## 2. Security & auth, 82 out of 100, up to 3.2 more on the total Why it scored 82: OAuth 2.0 with 20 Calendar scopes, from `calendar.freebusy` and `calendar.events.owned.readonly` up to full `calendar`, each classed as non-sensitive, sensitive or restricted (30). Read-only and free/busy-only scopes, and the MCP guide configures three read-only scopes. Nothing in the API confirms a delete (17). The MCP guide warns about indirect prompt injection and points to Model Armor, and tells operators to review AI-initiated actions (12). The Cloud console API dashboard shows traffic, errors by method and response code, and latency percentiles per project, but not a per-call log (8). Valid security.txt with a contact, an encryption key and the Google VRP bug bounty. We didn't check certifications this run (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 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. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 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. - 0 to 15, audit logs or per-call visibility for the operator. - 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. ## 3. Schema & documentation, 83 out of 100, up to 2.8 more on the total Why it scored 83: Google publishes a discovery document rather than OpenAPI, which is a machine-readable contract all the same (25). No llms.txt, per the 30 September check (0). Reference pages say what each method does and when to use patch over update, but we couldn't read the MCP tool descriptions (15). Typed parameters with enums such as `orderBy` and `eventTypes` (13). An error page that gives each reason code a recommended action, from `timeRangeEmpty` to `fullSyncRequired` (15). v3 in the path and dated release notes, latest 14 July 2026 (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 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. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 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. ## 4. Reliability, 90 out of 100, up to 2 more on the total Why it scored 90: The Google Workspace Status Dashboard lists Calendar with 365 days of incidents (20). Its last Calendar incidents were 31 May 2026 (56 minutes, several Workspace products) and 13 March 2026 (2 hours 30 minutes of US errors), with none since 3 July. The dashboard tracks the Calendar product rather than the API alone (30). 10,000 requests a minute per project, 600 a minute per user per project and 1,000,000 a day per project (15). 403 and 429 `usageLimits` errors with a truncated exponential backoff formula, client-supplied event IDs that return 409 on a duplicate, and ETags with 412 on a stale write (15). No SLA for the API found (0). The REST API is GA. The MCP server is a developer preview (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 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. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 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. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 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. ## 5. Transparency & trust, 79 out of 100, up to 1.8 more on the total Made of editorial 58, provenance 100. Why it scored 79: Closed service under Google's API terms, with Apache-2.0 client libraries (15). Google's privacy policy covers end users, and the Workspace data processing terms cover tenants, but we didn't find one retention statement for Calendar API data (18). Dated announcements ahead of changes, such as the 1 June notice for the 29 June GA of `writerWithoutPrivateAccess` and at least 90 days' notice promised before quota charges (15). Workspace sub-processor and data location pages exist, which we didn't recheck this run (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency): - 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. - 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors). - 0 to 20, a deprecation policy or notices with dates. - 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. ## 6. Agent ergonomics, 91 out of 100, up to 1.5 more on the total Why it scored 91: Responses size with `maxResults` and Google's standard `fields` partial responses (20). `pageToken`, `syncToken`, `timeMin` and `timeMax`, `q` and `singleEvents` for expanding recurrences (20). Error reasons an agent can act on, with the action written next to each one (20). Client-supplied event IDs make creates safe to retry and ETags guard updates. We found no readOnlyHint or destructiveHint on the MCP's write tools (16). Official client libraries in many languages, and most parameters are optional (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 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). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 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. ## 7. Maintenance & community, 87 out of 100, up to 1.1 more on the total Why it scored 87: @googleapis/calendar 20.0.1 on 24 September 2026, after a generated API update on 23 September (30). Release notes on 7 and 14 July plus that client release since 3 July (20). Dated release notes and public client repositories with active maintainers (12). Current official client libraries (15). Generated clients rebuilt by CI in google-api-nodejs-client, with commits up to 1 October (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 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. - 20, at least three releases or dated changelog entries in the last 90 days. - 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. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## What we couldn't check What 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. - Which scopes the MCP preview's create, update and delete tools need, given the guide configures only read-only scopes - Whether the MCP tools carry readOnlyHint or destructiveHint - Price per request above the 1,000,000-a-day threshold - unchecked: Workspace certifications and sub-processor list this run ## Weaknesses - Google calendars only - OAuth consent screen, Cloud project and app verification for restricted scopes before real users can connect - No slot finding or booking pages, only raw free/busy - MCP server limited to a developer preview programme - Price for use above the daily quota not yet published ## What costs an agent a turn today The notes we give agents before they call it. Each one is a workaround an agent shouldn't need. - Ask for `calendar.events.freebusy` when you only need availability, since it's non-sensitive and skips verification - Set your own event `id` on insert, and treat a 409 as already created - Use `singleEvents=true` with `orderBy=startTime` to expand recurring events when listing - On 410 `fullSyncRequired`, drop the stored `syncToken` and do a full sync - Back off exponentially on 403 and 429 `usageLimits`, up to 32 or 64 seconds ## What the review panel asked for - Open the MCP preview (2 reviews) - Publish the overage price (2 reviews) - Name write tool scopes - the overage price published with its start date - Publish the MCP tool descriptions and annotations - llms.txt - readable MCP tool descriptions - An SLA that names the API - Over-quota price - per-call audit log - document MCP write scopes ## When it's done Send 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.