◎ Discry Score
pipeboard.com
ai · API
C
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 99 (A)
Discry your API →
AI · RANK #34 OF 43

Pipeboard is Needs Work to agents.

Discry independently scored how well an AI agent can discover and understand the Pipeboard 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 · 52/100
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.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.Pass

Comprehension

55% of score · 88/100
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.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

  • An agent looking for Pipeboard would find it easily: it is MCP-native and listed on PulseMCP, Glama, and mcp.so, ships an API-focused llms.txt, and its robots.txt explicitly allows every major AI crawler (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, etc.).
  • Comprehension is strong: tool descriptions are task-oriented ('Create a new campaign with budget, objective, and targeting'), naming is consistently snake_case, read/write permission boundaries and rate limits are clearly documented, and multiple step-by-step workflow guides exist.
  • The biggest discovery gap is no machine-readable spec: there is no OpenAPI/Swagger file and no .well-known/mcp.json, so an agent building a direct integration must rely on MCP tools/list discovery or scrape the human-readable API reference page.
  • Despite being an agent-first product, it misses several agent signals: no AGENTS.md in the open-source repo and no llms-full.txt, leaving discovery weight concentrated in the (present) llms.txt.
  • Error recovery is deep for the flagship auth error (#3858385 has a full step-by-step fix) but is not systematized across the broader error surface, and code examples are largely single-interface (prompt + one curl) rather than multi-language.

What to change

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

  1. 01Publish a machine-readable interface: since the product is MCP-native, serve a .well-known/mcp.json with tool declarations and/or an OpenAPI spec for the direct API path — this is the single largest score lever (openApiSpec weight 5 + wellKnownMcp).
  2. 02Add an AGENTS.md to the meta-ads-mcp repo (and its sibling ad-platform repos) with setup, auth, and tool-usage context for coding agents.
  3. 03Add an llms-full.txt bundling full tool schemas and workflow examples into a single markdown file for single-fetch agent consumption.
  4. 04Expand error docs into a structured catalog covering the top 5-10 API/Meta errors with explicit recovery steps, matching the quality of the existing #3858385 guide.
  5. 05Provide multi-language code examples (Python / JS / curl) for the direct API, not just prompt-based walkthroughs and a single curl snippet.

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 token (Bearer header or ?token= query param)✓ Error format documented✓ Rate limits documented✕ Pagination documented✕ Idempotency documented

Auth is well documented: OAuth to connect ad accounts plus scoped Pipeboard API tokens (Bearer header or query param), with fine-grained per-tool and read-only permissions. Errors surface as JSON-RPC / Meta OAuthException codes and there is a dedicated recovery guide for the flagship auth error (#3858385). Rate limits are explicit (Meta's 200 calls/hour, with automatic exponential-backoff retries). Pagination is not documented as a pattern (some tools expose a limit arg only), and idempotency keys are not mentioned though writes use an explicit confirmation model.

See your own Discry Score.

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

Discry your API — free