◎ Discry Score
guru.com
productivity · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 92 (A)
Discry your API →
PRODUCTIVITY · RANK #5 OF 24

Guru is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Guru API from what’s public — not whether it’s usable. Below: every signal we checked, what’s costing the score, and what to change.

Discry your API — freeView the docs ↗

SCORED UNDER RUBRIC 1.2 · A full re-launch under Discry Score 2.5 — a new behavioral instrument, not comparable to these scores — is in progress.

Discovery

45% of score · 67/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Pass
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Pass
llms-full.txtA full-text bundle agents can load in one request.Fail
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Fail
.well-known/mcp.jsonA discoverable MCP manifest at a well-known path.Fail
MCP registryThe API is listed in a public MCP registry.Pass
robots.txt AI directivesrobots.txt allows (or explicitly guides) AI crawlers.Pass
SitemapA sitemap so agents can enumerate the docs surface.Fail

Comprehension

55% of score · 91/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Pass
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Pass
Error-recovery guidanceDocumented failure modes and how to recover from them.Partial
Answer-first formatThe answer leads; preamble does not bury it.Pass
Capability boundariesClear limits — what the API can and cannot do.Partial
Naming consistencyConsistent, predictable naming across endpoints.Pass
Heading hierarchyClean heading structure agents can navigate.Pass
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Pass
Token efficiencyDocs are concise enough to fit an agent context window.Pass

What we found

  • An agent discovering Guru would land immediately: a comprehensive, API-focused llms.txt at developer.getguru.com/llms.txt indexes every guide and endpoint, and each page is served as clean markdown via a .md suffix — near-ideal for LLM consumption.
  • Every API-reference page embeds the full OpenAPI 3.0 definition inline alongside realistic request/response examples (real UUIDs, real email addresses, working curl and Python snippets), so an agent can understand and call endpoints without guessing.
  • Guru ships an official MCP server (listed on PulseMCP, OAuth-based, no code setup), plus a Guru CLI and docs explicitly written for pairing with Claude Code / Cursor — signaling deliberate agent-readiness.
  • Discovery is dragged down by missing plumbing: no sitemap.xml, no llms-full.txt, no .well-known/mcp.json, and no AGENTS.md in a discoverable repo — an agent relying on those standard signals would come up empty.
  • An agent would hit boundaries silently: rate limits are unpublished and there is no dedicated error-recovery reference (e.g. what to do on a 429), so failure modes must be discovered by trial.

What to change

Prioritized by impact on discoverability. You (or your docs platform) deploy these — Discry never touches your API.

  1. 01Publish a rate-limits page (limits, headers like Retry-After, and 429 recovery guidance) and a dedicated errors reference mapping the top 5–10 error responses to concrete fixes — the biggest comprehension gap for agents chaining calls.
  2. 02Add a sitemap.xml covering the developer network (ReadMe supports this) so crawlers and agents relying on sitemaps can enumerate docs pages.
  3. 03Serve an llms-full.txt with the concatenated markdown body of core pages so agents can ingest the full corpus in one fetch rather than following dozens of .md links.
  4. 04Add an AGENTS.md to the public guru-py-sdk repo (and any other primary repos) to guide coding agents working against the SDK.
  5. 05Expose a .well-known/mcp.json advertising the official MCP server's tools and auth so MCP-aware clients can auto-discover it from the domain.

Execution coverage · INFORMATIONAL, UNSCORED

Whether an agent can actually complete a call and recover from errors is the deeper Audit layer — documented here, but not part of the Discry Score.

Basic Auth (User Token — read/write)Basic Auth (Collection Token — read-only)OAuth 2.0Impersonation Tokens✕ Error format documented✕ Rate limits documented✓ Pagination documented✕ Idempotency documented

Auth is thoroughly documented (Basic Auth via User/Collection tokens plus OAuth 2.0 and impersonation tokens). Pagination is clearly documented as cursor-based via a Link header. Rate limits are not publicly documented (Guru states limits are enforced but unpublished), idempotency is not addressed, and there is no dedicated structured error-format reference — error responses surface only through per-endpoint OpenAPI response codes and workflow-guide notes.

See your own Discry Score.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free