◎ Discry Score
slack.com
productivity · API
C
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 92 (A)
Discry your API →
PRODUCTIVITY · RANK #15 OF 24

Slack is Needs Work to agents.

Discry independently scored how well an AI agent can discover and understand the Slack 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 · 69/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Partial
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Fail
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.Partial

Comprehension

55% of score · 72/100
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.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.Partial
Token efficiencyDocs are concise enough to fit an agent context window.Partial

What we found

  • Slack's llms.txt is the clearest example of a failed llmsTxtQuality check — the file exists and is well-structured, but covers the product (pricing, features, customer stories) rather than the API, making it useless for agents integrating with the developer platform
  • Multi-step workflow documentation is limited: Bolt framework quickstarts exist but dedicated end-to-end API workflow guides (e.g., create app > set scopes > post message > handle events) are sparse
  • Error recovery guidance is partial — each method documents 30-50 error codes with descriptions, but few include actionable recovery steps like 'check scope permissions' or 'verify channel membership'
  • Strong programmatic discovery signals exist: OpenAPI spec, official MCP server at mcp.slack.com, and AGENTS.md in python-slack-sdk — but they are undermined by the product-focused llms.txt and missing llms-full.txt
  • The sitemap covers only marketing pages, excluding all api.slack.com and docs.slack.dev developer documentation

What to change

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

  1. 01Create a developer-focused llms.txt at api.slack.com or docs.slack.dev covering core API capabilities, auth patterns, and links to the OpenAPI spec — this single change would fix both llmsTxt and llmsTxtQuality
  2. 02Add .well-known/mcp.json at api.slack.com pointing to mcp.slack.com/mcp with tool declarations and OAuth configuration
  3. 03Publish llms-full.txt with markdown covering the top 20-30 API methods, auth flow, and rate limit tiers
  4. 04Add end-to-end workflow guides: create app > configure scopes > install > post messages > handle events > manage threads
  5. 05Enhance error tables with actionable recovery steps for the top 10 most common errors per method

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.

oauth2bot_tokenuser_tokenapp_token✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

OAuth 2.0 with bot/user/app-level tokens. JSON error responses with ok:false and error codes. Tiered rate limits (1-4 + special) with Retry-After headers. Cursor-based pagination with next_cursor. No idempotency key support.

See your own Discry Score.

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

Discry your API — free