Unitedhealthgroupunitedhealthgroup.com
UnitedHealthGroup's API program shows meaningful strengths in machine-readable contract structure and schema quality, but partner outcomes are held back most severely in two areas: agents and partners cannot reliably execute or trust the API surface (missing runnable examples, idempotency guidance, rate-limit signaling, and RFC 9457 errors), and the program is largely invisible to both automated agents and self-serve partners (no registry presence, no agent instructions file, no changelog). Prioritize making the API executable and trustworthy first, then close the discoverability and onboarding gaps so partners can find, evaluate, and integrate without a sales conversation.
API DesignA clean, typed, well-governed API contract agents can reason about1 pass2 warn2 fail64C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| warn | Schema coverage & depthvia spec | 20.8/25 | Medium parameter complexity (avg 1.7 params/op; nested/body schemas present). Investigated: spec 83%. | Typed, complete request/response schemas are what make agent function-calling possible. |
| warn | Machine-readable, versioned contractvia spec | 18.8/25 | info.version="v3" set but no versioning scheme (URL / header / media type) detected. Investigated: spec 75%, docs 50%. | A current OpenAPI version with a declared versioning scheme lets agents reason about the contract. |
| pass | Security & governance hygienevia spec | 15/15 | No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 50%. | No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel. |
| fail | Auth declared & discoverablevia spec | 0/25 | securitySchemes declared but never applied. Investigated: spec 0%, docs 0%. | Agents can only authenticate when auth is declared, scoped, and discoverable. |
| fail | Example coveragevia spec | 0/10 | 0% example coverage. Investigated: spec 0%. | Examples carry shape semantics schemas under-specify — for humans and agents alike. |
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples1 pass0 warn3 fail53D
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Self-service developer portalvia docs | 29/29 | Signup page at https://www.unitedhealthgroup.com/page-not-found.html; no free-tier language detected in docs/pricing. Investigated: docs 100%. | Self-serve key/account creation is the fast first call for partners, with no sales gate. |
| fail | Quickstart presentvia docs | 0/25 | No quickstart/getting-started page found at the conventional paths. Investigated: docs 0%. | A quickstart is the fastest path from landing page to first successful call. |
| fail | Description completenessvia spec | 0/15 | 30% description completeness. Investigated: spec 0%. | Complete descriptions are the context humans and agents need to use endpoints. |
| fail | Changelog publishedvia spec | 0/13 | No changelog URL or mention found in spec metadata. Investigated: spec 0%, docs 0%. | A published changelog lets partners track changes without surprise. |
| na | Code samples in docs | —/18 | No surface produced evidence for this capability in this run. | Multi-language samples shorten time-to-first-call. |
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs0 pass3 warn1 fail60C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| warn | llms.txt present, valid & comprehensivevia docs | 27.9/30 | 39/40 same-origin links resolve (98%); 1 broken. Investigated: docs 93%. | A valid, comprehensive llms.txt is the machine-readable entry point for agents. |
| warn | Docs reachable, not hard auth-gatedvia docs | 15/30 | 40 JavaScript redirect(s) detected across 40 pages. Investigated: docs 50%. | Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics. |
| warn | Crawlable / AEOvia wellknown | 6/12 | No sitemap discoverable via robots.txt or /sitemap.xml on the docs host. Investigated: wellknown 50%. | Bots allowed plus a fresh sitemap make docs findable by agent crawlers. |
| fail | Registry & SDK presencevia docs | 0/28 | Not indexed on Context7 — agents can't pull this API's docs on demand via Context7. Investigated: docs 0%, sdk 0%, cli 0%. | Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look. |
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs1 pass1 warn2 fail59D
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Operation purpose clarityvia spec | 25/25 | 100% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%. | Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice. |
| warn | Agent-navigable, token-efficient docsvia docs | 15.1/22 | No pages support .md URLs (0/40 tested). Investigated: docs 69%. | Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly. |
| fail | Machine-readable errors (RFC 9457)via spec | 0/28 | No 4xx/5xx response codes (or default error response) documented anywhere in the spec. Investigated: spec 0%, docs 0%. | RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens. |
| fail | Agent instructions file (AGENTS.md)via wellknown | 0/10 | No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%. | An AGENTS.md gives coding agents explicit setup, auth, and usage instructions to interpret and operate the API — beyond llms.txt's link index. |
| na | Docs structured data | —/8 | No surface produced evidence for this capability in this run. | Structured data (JSON-LD/schema.org) on docs pages gives agents an unambiguous parse target and is what answer engines cite. Detected on the JS-rendered head (Firecrawl) for a bounded page budget, so JS-injected JSON-LD is now caught; pages we can't render are excluded rather than failed. |
| na | Description consistency across surfaces | —/7 | Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare. | Every surface tells the same story about what the product is. |
Agent UsabilityAgents have the context to use your APIs reliably, not just find them1 pass0 warn3 fail48F
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Sandbox separationvia spec | 20/20 | Sandbox server declared but no distinguishable test credentials in scheme descriptions. Investigated: spec 100%, docs 100%. | An isolated environment lets agents exercise destructive operations safely. |
| fail | Idempotency documentedvia spec | 0/27 | 0% of mutating operations document idempotency. Investigated: spec 0%, docs 0%. | Documented idempotency lets agents retry safely. |
| fail | Rate-limit signalingvia spec | 0/22 | No rate-limit response headers documented. Investigated: spec 0%, docs 0%. | Machine-readable rate-limit headers let agents throttle adaptively. |
| fail | Runnable collection with test scriptsvia platform | 0/9 | No public Postman workspace discovered for the org. Investigated: platform 0%. | A public, maintained collection with assertions is runnable truth agents validate against. |
| na | Pagination documented & consistent | —/22 | No surface produced evidence for this capability in this run. | Consistent, documented pagination lets agents traverse collections. |
Resources Discovered
The public resources we found for Unitedhealthgroup — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.
| APIs analyzed | 1 — Medical Network Eligibility v3 |
|---|