{
  "fixes": {
    "slug": "particle-health",
    "name": "Particle Health",
    "listing": "https://www.anchorterminal.com/tools/particle-health",
    "markdown": "# Fix list: Particle Health\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/particle-health, the October 2026 research run, assessed 14 October 2026. Grade D, 48.6 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 Particle Health: 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, 5 out of 100, up to 11.9 more on the total\n\nWhy it scored 5: Read with the hosted rubric. No x402, MPP or L402 (0). No published prices (0). A sandbox with synthetic patients exists, but credentials come from a representative and the free sign-up link did not resolve (5 of 20). A person must be provisioned by Particle (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, 58 out of 100, up to 8.4 more on the total\n\nWhy it scored 58: Read with the hosted lines. status.particlehealth.com on Statuspage with 7 components and history (20). In the last 90 days, CommonWell traffic was disrupted for about five and a half hours on 5 August 2026, marked critical, and a Google Cloud zone outage on 1 September raised risk with no impact recorded. We read the first as a network-side outage, as for the other network listings (15 of 30). Rate limits exist per project with no numbers, apart from the sandbox's 500 queries a day (5 of 15). 429 with a backoff recommendation, no Retry-After or idempotency guidance (8 of 15). No SLA found in public (0). The v2 APIs are generally available (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. Agent ergonomics, 53 out of 100, up to 7.6 more on the total\n\nWhy it scored 53: FHIR by resource type or ID, flat data filtered by domain, and Snapshot AI summaries where enabled (17 of 25). Continuation tokens and filters (16 of 20). Standard HTTP codes with some context (12 of 20). No idempotency keys or safe-retry guidance (3 of 20). No official SDK (5 of 15).\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## 4. Security \u0026 auth, 57 out of 100, up to 7.5 more on the total\n\nWhy it scored 57: OAuth 2.0 client credentials with a mandatory project scope, 60-minute tokens, rotation that expires old credentials, and IAM roles on service accounts (27 of 30). Project-scoped tokens, roles beyond owner on request, purpose-of-use rules and a delegation of authority policy, with deletes allowed and no confirmation step (13 of 20). Records and AI summaries from outside organisations, with no prompt-injection guidance (3 of 15). No audit log for operators found (2 of 15). HITRUST and SOC 2 claimed for the API platform, a vulnerability submission form, no bug bounty or security.txt (12 of 20).\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## 5. Maintenance \u0026 community, 27 out of 100, up to 6.4 more on the total\n\nWhy it scored 27: No dated release was found. Docs pages were updated on 13 October 2026, and v2 subscription endpoints sit beside v1, which we read as recent change without a release record (20 of 30). No changelog (0). Support through a representative, with no public record (5 of 15). No official SDK found (0 of 15). A maintained Postman collection (2 of 10).\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## 6. Schema \u0026 documentation, 69 out of 100, up to 5 more on the total\n\nWhy it scored 69: OpenAPI fragments on each reference page, with no single specification file found (18 of 25). llms.txt and Markdown pages (10). A developer guide by path (Workbench, Signal) and global conventions for IDs, auth and pagination (14 of 20). Typed inputs in the fragments (11 of 15). A Postman collection and an error code table with context (11 of 15). Versioned /api/v1 and /api/v2 paths and legacy flows marked, but no changelog, which returns 404 (5 of 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## 7. Transparency \u0026 trust, 48 out of 100, up to 4.6 more on the total\n\nMade of editorial 27, provenance 69.\n\nWhy it scored 48: Closed service. The public terms date from 2020 and cover only the website, and no developer or API terms were found (10 of 30). The privacy policy (July 2026) covers the site only and keeps de-identified aggregate data, with no retention periods or public DPA (8 of 30). Legacy flows are labelled as supported for existing customers, with no dates (5 of 20). Google Cloud is named as the platform, with no sub-processor list or regions (4 of 20).\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- Domain age: particlehealth.com, registered 2017-11-22 (8 years) (11 of 15)\n- Terms of service: read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points (5.1 of 10)\n- Privacy policy: read, states 5 of the 8 things a reader expects (7.8 of 10)\n- Changelog: not found (0 of 10)\n- security.txt: not found (0 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- portal.particlehealth.com, the target of the 'play for free' link, had no DNS record on 14 October 2026, so the free route could not be checked\n- Production base URL not confirmed in the pages read, which show the sandbox host\n- No developer terms, SLA or DPA were found in public\n\n## Weaknesses\n\n- Credentials come from a Particle representative, and the 'play for free' sign-up domain did not resolve\n- Rate limits vary with load and have no published numbers\n- No changelog, SLA or developer terms in public\n- No audit log for operators was found\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- Pass `projects/\u003cproject_id\u003e` as the scope when requesting a token, and request a new one every 60 minutes\n- Poll Get Query Status, or wait for the query-complete webhook, before reading FHIR or flat data\n- Back off on 429, since limits change with system load\n- Pass continuation tokens back verbatim when paging\n- Use the published synthetic patients in sandbox, and stay under 500 queries a day\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": "D",
    "score": 48.6,
    "assessed": "2026-10-14",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 5,
        "maxGain": 11.9,
        "reason": "Read with the hosted rubric. No x402, MPP or L402 (0). No published prices (0). A sandbox with synthetic patients exists, but credentials come from a representative and the free sign-up link did not resolve (5 of 20). A person must be provisioned by Particle (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": 58,
        "maxGain": 8.4,
        "reason": "Read with the hosted lines. status.particlehealth.com on Statuspage with 7 components and history (20). In the last 90 days, CommonWell traffic was disrupted for about five and a half hours on 5 August 2026, marked critical, and a Google Cloud zone outage on 1 September raised risk with no impact recorded. We read the first as a network-side outage, as for the other network listings (15 of 30). Rate limits exist per project with no numbers, apart from the sandbox's 500 queries a day (5 of 15). 429 with a backoff recommendation, no Retry-After or idempotency guidance (8 of 15). No SLA found in public (0). The v2 APIs are generally available (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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 53,
        "maxGain": 7.6,
        "reason": "FHIR by resource type or ID, flat data filtered by domain, and Snapshot AI summaries where enabled (17 of 25). Continuation tokens and filters (16 of 20). Standard HTTP codes with some context (12 of 20). No idempotency keys or safe-retry guidance (3 of 20). No official SDK (5 of 15).",
        "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": 57,
        "maxGain": 7.5,
        "reason": "OAuth 2.0 client credentials with a mandatory project scope, 60-minute tokens, rotation that expires old credentials, and IAM roles on service accounts (27 of 30). Project-scoped tokens, roles beyond owner on request, purpose-of-use rules and a delegation of authority policy, with deletes allowed and no confirmation step (13 of 20). Records and AI summaries from outside organisations, with no prompt-injection guidance (3 of 15). No audit log for operators found (2 of 15). HITRUST and SOC 2 claimed for the API platform, a vulnerability submission form, no bug bounty or security.txt (12 of 20).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 27,
        "maxGain": 6.4,
        "reason": "No dated release was found. Docs pages were updated on 13 October 2026, and v2 subscription endpoints sit beside v1, which we read as recent change without a release record (20 of 30). No changelog (0). Support through a representative, with no public record (5 of 15). No official SDK found (0 of 15). A maintained Postman collection (2 of 10).",
        "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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 69,
        "maxGain": 5,
        "reason": "OpenAPI fragments on each reference page, with no single specification file found (18 of 25). llms.txt and Markdown pages (10). A developer guide by path (Workbench, Signal) and global conventions for IDs, auth and pagination (14 of 20). Typed inputs in the fragments (11 of 15). A Postman collection and an error code table with context (11 of 15). Versioned /api/v1 and /api/v2 paths and legacy flows marked, but no changelog, which returns 404 (5 of 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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 48,
        "maxGain": 4.6,
        "reason": "Closed service. The public terms date from 2020 and cover only the website, and no developer or API terms were found (10 of 30). The privacy policy (July 2026) covers the site only and keeps de-identified aggregate data, with no retention periods or public DPA (8 of 30). Legacy flows are labelled as supported for existing customers, with no dates (5 of 20). Google Cloud is named as the platform, with no sub-processor list or regions (4 of 20).",
        "blend": "editorial 27, provenance 69",
        "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": "Domain age",
        "value": "particlehealth.com, registered 2017-11-22 (8 years)",
        "points": 11,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points",
        "points": 5.1,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 5 of the 8 things a reader expects",
        "points": 7.8,
        "max": 10
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "portal.particlehealth.com, the target of the 'play for free' link, had no DNS record on 14 October 2026, so the free route could not be checked",
      "Production base URL not confirmed in the pages read, which show the sandbox host",
      "No developer terms, SLA or DPA were found in public"
    ],
    "weaknesses": [
      "Credentials come from a Particle representative, and the 'play for free' sign-up domain did not resolve",
      "Rate limits vary with load and have no published numbers",
      "No changelog, SLA or developer terms in public",
      "No audit log for operators was found"
    ],
    "agentNotes": [
      "Pass `projects/\u003cproject_id\u003e` as the scope when requesting a token, and request a new one every 60 minutes",
      "Poll Get Query Status, or wait for the query-complete webhook, before reading FHIR or flat data",
      "Back off on 429, since limits change with system load",
      "Pass continuation tokens back verbatim when paging",
      "Use the published synthetic patients in sandbox, and stay under 500 queries a day"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-14",
    "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"
  }
}