{
  "fixes": {
    "slug": "microsoft-advertising-api",
    "name": "Microsoft Advertising API",
    "listing": "https://www.anchorterminal.com/tools/microsoft-advertising-api",
    "markdown": "# Fix list: Microsoft Advertising API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/microsoft-advertising-api, the October 2026 research run, assessed 8 October 2026. Grade C, 60.3 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 Microsoft Advertising 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, 30 out of 100, up to 8.8 more on the total\n\nWhy it scored 30: No x402, MPP or L402 (0). No fee for API access was found, and none is stated as waived. Ad spend is set by auction, so no unit price is published (10). The sandbox needs no payment method and takes a shared developer token (20). A person signs up, registers an Entra app and grants consent in a browser (0).\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. Reliability, 60 out of 100, up to 8 more on the total\n\nWhy it scored 60: Graded on the public API, read with the hosted lines. Platform health blog at status.ads.microsoft.com with areas for each API and dated posts (20). 40 posts from 20 July to 7 October 2026, 21 tagged Reporting API and all of those for delayed data, from three hours to six days. None reports the Campaign Management, Bulk, Customer Management or Ad Insight APIs down. Scored between minor and major for the frequency (15). Throttling is documented without numbers, and the Bulk and Reporting limits are called internal and subject to change (5). Wait 60 seconds after error 117 and up to 15 minutes after Bulk error 4204, with partial success on writes, but no idempotency key found (10). No SLA found (0). Version 13 is generally available. The MCP server is in open beta and isn't the surface graded (10).\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## 3. Security \u0026 auth, 60 out of 100, up to 7 more on the total\n\nWhy it scored 60: OAuth 2.0 through Entra ID or Google with refresh tokens and required multi-factor authentication, but one scope, `msads.manage`, covers every read and write (22). Access is limited by user role, with a read-only Viewer role and per-account access, and the MCP server is read-only. Nothing asks for confirmation before a delete (13). Search term reports and ad text return content written by outsiders, and no injection guidance was found (3). A campaign change history report and a `TrackingId` per call (10). MSRC disclosure policy and bounty, though microsoft.com's security.txt expired on 23 September 2026. Certifications covering Microsoft Advertising weren't checked (12).\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. Agent ergonomics, 63 out of 100, up to 6 more on the total\n\nWhy it scored 63: Reports take a chosen column list and Get operations take IDs and `ReturnAdditionalFields`, but entity responses return whole objects (15). `PageInfo` paging and predicates on Search operations, report filters and scopes, and entity selection on bulk downloads (17). Numeric and symbolic error codes, a `TrackingId` on every response and `PartialErrors` per item, though SOAP faults arrive as HTTP 500 and some failures are an unmapped internal error (15). No idempotency key or validate-only mode found. Partial update on most campaign objects is the only retry aid (5). SDKs for .NET, Java, Python and PHP. Each call needs a token and up to three more headers (11).\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## 5. Schema \u0026 documentation, 79 out of 100, up to 3.4 more on the total\n\nWhy it scored 79: A public WSDL for each of the six SOAP services, and REST URLs with JSON templates on every operation page. No public OpenAPI file was found, only a generated `openapi_client` inside the SDKs (15). learn.microsoft.com/llms.txt returns 404, but every page is returned as Markdown for `Accept: text/markdown` (10). Reference pages state each element's purpose, limits and required headers, with guides per service (15). Typed data objects and value sets, required elements marked (13). Request and response templates in SOAP and JSON with ValueHere placeholders, code examples in four languages and an operation error code list (11). Version 13 with dated monthly release notes (15).\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## 6. Maintenance \u0026 community, 61 out of 100, up to 3.4 more on the total\n\nWhy it scored 61: SDK 13.0.30 published on 29 September 2026, and `msads` 13.0.30 reached PyPI on 30 September (30). Two dated release-note entries (August and September 2026) and two SDK releases in the last 90 days, short of three (0). The Python SDK repository shows 54 open issues, two from July 2026 with no reply, while release pull requests merge within days. Microsoft says it monitors the Q\u0026A forum, which we didn't check (10). Current official SDKs in four languages (15). Azure Pipelines CI is configured, its matrix names Python 3.7 while the docs require 3.8, and HISTORY.rst carries three entries dated 2027 (6).\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## 7. Transparency \u0026 trust, 64 out of 100, up to 3.2 more on the total\n\nMade of editorial 38, provenance 90.\n\nWhy it scored 64: Closed service with MIT SDKs. The Microsoft Advertising Agreement page renders only with JavaScript, so we couldn't read the terms (10). The Microsoft privacy statement applies, and the docs give reporting data retention periods, but no API-specific retention statement was found (12). SOAP's end date of 31 January 2027 is announced with migration guides, and the release notes carry a breaking-changes section (16). Sub-processors and data locations for Microsoft Advertising weren't checked (0).\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: published, but our reader couldn't read it (7 of 10)\n- Privacy policy: read, states 8 of the 8 things a reader expects, and has 1 clause that costs points (8 of 10)\n- security.txt: published but past its Expires date (5 of 10)\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- unchecked: the Microsoft Advertising Agreement and any API-specific terms, because help.ads.microsoft.com renders only with JavaScript\n- unchecked: sub-processors, data locations and certifications covering Microsoft Advertising\n- unchecked: how quickly the Microsoft Q\u0026A forum answers, and GitHub stars and issue counts beyond the GitHub API figures\n- Whether a production developer token is issued at once or after review. The docs describe a Request Token button and no approval step\n- Whether Microsoft will publish an OpenAPI file for the REST API, and what the numeric call limits are\n- Whether the MCP tools carry readOnlyHint annotations, and when the server leaves open beta\n- The bulk upload row limit is given as 2.5 million on the sandbox page and 4 million on the services protocol page\n\n## Weaknesses\n\n- Call-rate limits carry no numbers. The docs describe a 60-second sliding window, and call the Bulk and Reporting limits internal and subject to change\n- No public OpenAPI file found. The contract is six WSDLs for SOAP, which retires on 31 January 2027, and a generated client inside the SDKs\n- One OAuth scope, `msads.manage`, covers reads and writes alike\n- 21 status posts tagged Reporting API between 20 July and 7 October 2026, all for delayed reporting data, one lasting six days\n- No idempotency key or validate-only mode found, so a retried add can create a duplicate\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- Build and test against the sandbox hosts (`*.api.sandbox.bingads.microsoft.com`) with developer token BBD37VB98. Sandbox and production credentials are separate\n- Send `Authorization: Bearer \u003ctoken\u003e`, `DeveloperToken`, `CustomerId` and `CustomerAccountId` on REST calls. Use the account ID, never the eight-character account number\n- Create campaigns with `Status` set to `Paused`, then read them back before activating. No validate-only mode was found\n- On error 117 (CallRateExceeded) wait 60 seconds. On Bulk error 4204 wait up to 15 minutes\n- Read `PartialErrors` on every add, update and delete. A call can succeed for some items and fail for others\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": "C",
    "score": 60.3,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No x402, MPP or L402 (0). No fee for API access was found, and none is stated as waived. Ad spend is set by auction, so no unit price is published (10). The sandbox needs no payment method and takes a shared developer token (20). A person signs up, registers an Entra app and grants consent in a browser (0).",
        "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": "reliability",
        "name": "Reliability",
        "score": 60,
        "maxGain": 8,
        "reason": "Graded on the public API, read with the hosted lines. Platform health blog at status.ads.microsoft.com with areas for each API and dated posts (20). 40 posts from 20 July to 7 October 2026, 21 tagged Reporting API and all of those for delayed data, from three hours to six days. None reports the Campaign Management, Bulk, Customer Management or Ad Insight APIs down. Scored between minor and major for the frequency (15). Throttling is documented without numbers, and the Bulk and Reporting limits are called internal and subject to change (5). Wait 60 seconds after error 117 and up to 15 minutes after Bulk error 4204, with partial success on writes, but no idempotency key found (10). No SLA found (0). Version 13 is generally available. The MCP server is in open beta and isn't the surface graded (10).",
        "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": "security",
        "name": "Security \u0026 auth",
        "score": 60,
        "maxGain": 7,
        "reason": "OAuth 2.0 through Entra ID or Google with refresh tokens and required multi-factor authentication, but one scope, `msads.manage`, covers every read and write (22). Access is limited by user role, with a read-only Viewer role and per-account access, and the MCP server is read-only. Nothing asks for confirmation before a delete (13). Search term reports and ad text return content written by outsiders, and no injection guidance was found (3). A campaign change history report and a `TrackingId` per call (10). MSRC disclosure policy and bounty, though microsoft.com's security.txt expired on 23 September 2026. Certifications covering Microsoft Advertising weren't checked (12).",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 63,
        "maxGain": 6,
        "reason": "Reports take a chosen column list and Get operations take IDs and `ReturnAdditionalFields`, but entity responses return whole objects (15). `PageInfo` paging and predicates on Search operations, report filters and scopes, and entity selection on bulk downloads (17). Numeric and symbolic error codes, a `TrackingId` on every response and `PartialErrors` per item, though SOAP faults arrive as HTTP 500 and some failures are an unmapped internal error (15). No idempotency key or validate-only mode found. Partial update on most campaign objects is the only retry aid (5). SDKs for .NET, Java, Python and PHP. Each call needs a token and up to three more headers (11).",
        "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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 79,
        "maxGain": 3.4,
        "reason": "A public WSDL for each of the six SOAP services, and REST URLs with JSON templates on every operation page. No public OpenAPI file was found, only a generated `openapi_client` inside the SDKs (15). learn.microsoft.com/llms.txt returns 404, but every page is returned as Markdown for `Accept: text/markdown` (10). Reference pages state each element's purpose, limits and required headers, with guides per service (15). Typed data objects and value sets, required elements marked (13). Request and response templates in SOAP and JSON with ValueHere placeholders, code examples in four languages and an operation error code list (11). Version 13 with dated monthly release notes (15).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 61,
        "maxGain": 3.4,
        "reason": "SDK 13.0.30 published on 29 September 2026, and `msads` 13.0.30 reached PyPI on 30 September (30). Two dated release-note entries (August and September 2026) and two SDK releases in the last 90 days, short of three (0). The Python SDK repository shows 54 open issues, two from July 2026 with no reply, while release pull requests merge within days. Microsoft says it monitors the Q\u0026A forum, which we didn't check (10). Current official SDKs in four languages (15). Azure Pipelines CI is configured, its matrix names Python 3.7 while the docs require 3.8, and HISTORY.rst carries three entries dated 2027 (6).",
        "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"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 64,
        "maxGain": 3.2,
        "reason": "Closed service with MIT SDKs. The Microsoft Advertising Agreement page renders only with JavaScript, so we couldn't read the terms (10). The Microsoft privacy statement applies, and the docs give reporting data retention periods, but no API-specific retention statement was found (12). SOAP's end date of 31 January 2027 is announced with migration guides, and the release notes carry a breaking-changes section (16). Sub-processors and data locations for Microsoft Advertising weren't checked (0).",
        "blend": "editorial 38, provenance 90",
        "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"
      }
    ],
    "provenance": [
      {
        "label": "Terms of service",
        "value": "published, but our reader couldn't read it",
        "points": 7,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 8 of the 8 things a reader expects, and has 1 clause that costs points",
        "points": 8,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "published but past its Expires date",
        "points": 5,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: the Microsoft Advertising Agreement and any API-specific terms, because help.ads.microsoft.com renders only with JavaScript",
      "unchecked: sub-processors, data locations and certifications covering Microsoft Advertising",
      "unchecked: how quickly the Microsoft Q\u0026A forum answers, and GitHub stars and issue counts beyond the GitHub API figures",
      "Whether a production developer token is issued at once or after review. The docs describe a Request Token button and no approval step",
      "Whether Microsoft will publish an OpenAPI file for the REST API, and what the numeric call limits are",
      "Whether the MCP tools carry readOnlyHint annotations, and when the server leaves open beta",
      "The bulk upload row limit is given as 2.5 million on the sandbox page and 4 million on the services protocol page"
    ],
    "weaknesses": [
      "Call-rate limits carry no numbers. The docs describe a 60-second sliding window, and call the Bulk and Reporting limits internal and subject to change",
      "No public OpenAPI file found. The contract is six WSDLs for SOAP, which retires on 31 January 2027, and a generated client inside the SDKs",
      "One OAuth scope, `msads.manage`, covers reads and writes alike",
      "21 status posts tagged Reporting API between 20 July and 7 October 2026, all for delayed reporting data, one lasting six days",
      "No idempotency key or validate-only mode found, so a retried add can create a duplicate"
    ],
    "agentNotes": [
      "Build and test against the sandbox hosts (`*.api.sandbox.bingads.microsoft.com`) with developer token BBD37VB98. Sandbox and production credentials are separate",
      "Send `Authorization: Bearer \u003ctoken\u003e`, `DeveloperToken`, `CustomerId` and `CustomerAccountId` on REST calls. Use the account ID, never the eight-character account number",
      "Create campaigns with `Status` set to `Paused`, then read them back before activating. No validate-only mode was found",
      "On error 117 (CallRateExceeded) wait 60 seconds. On Bulk error 4204 wait up to 15 minutes",
      "Read `PartialErrors` on every add, update and delete. A call can succeed for some items and fail for others"
    ],
    "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"
  }
}