◎ Discry Score
zapier.com
devtools · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 96 (A)
Discry your API →
DEVTOOLS · RANK #14 OF 39

Zapier is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Zapier 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.Fail
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.Pass
.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.Pass

Comprehension

55% of score · 96/100
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.Pass
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

  • Zapier has the most agent-intentional documentation of any API scanned: a hierarchical llms.txt system with root map at zapier.com/llms.txt, topic anchors (#mcp, #sdk, #embed), and per-subdomain indexes — purpose-built for agent discovery
  • All documentation pages are available as .md URLs (e.g., docs.zapier.com/sdk/quickstart.md), and the quickstart includes 'Open in Codex' deep links for one-click agent setup — a level of agent-native design rarely seen
  • The SDK reference is comprehensive (155KB, 126 sections) with TypeScript examples for every method, clear parameter tables, and return type documentation — an agent can immediately start coding without ambiguity
  • Despite exceptional documentation quality, Zapier has no public OpenAPI spec for its own API — ironic for a platform that helps other APIs integrate, and it costs 5 points in discovery scoring
  • AGENTS.md exists in the zapier/sdk repo with explicit rules for coding agents: 'no hallucinating method names; use listActions / getActionInputFieldsSchema to discover capabilities at runtime'

What to change

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

  1. 01Publish an OpenAPI spec for the Zapier SDK/API — this is the single biggest discovery gap (weight: 5) and ironic for an API integration platform
  2. 02Add .well-known/mcp.json at zapier.com pointing to the official Zapier MCP server for standardized machine discovery
  3. 03Add llms-full.txt combining the SDK reference, MCP docs, and integration builder docs into a single comprehensive markdown file
  4. 04Add more explicit error recovery guidance in the SDK reference — currently error handling patterns are sparse compared to the exceptional quality of everything else

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.

oauth2api_keyclient_credentials✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

TypeScript SDK with multiple auth options (browser-based, client credentials, direct token). JSON responses with error details. Usage limits and billing documented for MCP and SDK. Cursor-based pagination via SDK methods. No idempotency documentation found.

See your own Discry Score.

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

Discry your API — free