◎ Discry Score
coresignal.com
analytics · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 92 (A)
Discry your API →
ANALYTICS · RANK #11 OF 29

Coresignal is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Coresignal 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 · 60/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Partial
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.Partial

Comprehension

55% of score · 87/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Partial
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Partial
Error-recovery guidanceDocumented failure modes and how to recover from them.Pass
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

  • An agent can read Coresignal's docs almost entirely as clean markdown: the GitBook-hosted site exposes a per-page .md endpoint, a comprehensive API-focused llms.txt index, and a built-in `?ask=` query mechanism — near-ideal for LLM consumption.
  • An agent discovering Coresignal for the first time would find an official, remote MCP server (mcp.coresignal.com) listed on PulseMCP and documented in-repo, letting it connect to company/employee/jobs data without wiring raw REST calls.
  • Endpoint pages are strongly task-oriented — each API states what you accomplish ('Get a comprehensive view of any company…'), and the search→collect→enrich pattern, rate limits, credits, and response codes are all clearly tabulated.
  • Discovery is dragged down by missing agent-standard files: no llms-full.txt, no .well-known/mcp.json, and no AGENTS.md in the coresignal-mcp repo — so an agent gets no single self-describing manifest and must assemble context from multiple pages.
  • No first-party OpenAPI/Swagger spec is published; docs rely on Postman/cURL templates with placeholder values ({company_id}, {API Key}), so an agent cannot auto-generate a typed client and must infer request shapes from prose.

What to change

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

  1. 01Publish a first-party OpenAPI 3.x spec (e.g. docs.coresignal.com/openapi.json) covering the v2 Company/Employee/Jobs endpoints — this is the single highest-impact fix, enabling agents to auto-generate typed clients instead of parsing cURL templates.
  2. 02Add an AGENTS.md to the Coresignal-com/coresignal-mcp repo (and any client repos) summarizing auth, base URL, core endpoints, and the search→collect workflow so coding agents get instant context.
  3. 03Add a .well-known/mcp.json manifest advertising the remote MCP server and its tools, so MCP-aware agents can auto-discover it without a registry lookup.
  4. 04Replace placeholder example values ({company_id}, {API Key}) with realistic sample IDs and a runnable end-to-end request, so copy-pasted examples work with minimal edits.
  5. 05Serve an llms-full.txt (or link the .md bundle) and ensure the root robots.txt sitemap covers the docs subdomain, tightening the discovery surface for crawlers and agents.

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.

API key (apikey header)✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Execution characteristics are well documented: single API-key header auth, per-endpoint rate limits (requests/second), a full response-code reference with recovery hints, and dedicated pagination pages (search-after / Elasticsearch DSL). No formal idempotency keys, though bulk collect returns 409 on duplicate POSTs. Claims are documentation-only and would need live testing to verify.

See your own Discry Score.

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

Discry your API — free