◎ Discry Score
atlassian.com
devtools · API
C
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 96 (A)
Discry your API →
DEVTOOLS · RANK #24 OF 39

Atlassian is Needs Work to agents.

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

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

  • Atlassian has invested heavily in MCP infrastructure — an official Remote MCP Server securely connects Jira and Confluence with LLMs, and AGENTS.md exists in the atlascode VS Code extension repo — but basic discovery signals like llms.txt are completely absent
  • The OpenAPI spec for Jira Cloud is comprehensive and downloadable (swagger-v3.v3.json), covering the full REST API surface — this is the strongest discovery signal and critical for agent auto-discovery
  • No llms.txt, llms-full.txt, or .well-known/mcp.json despite having an official MCP server — an agent looking for Atlassian's agent-friendly endpoints via standard discovery paths would fail entirely
  • Documentation quality for individual endpoints is strong with task-oriented descriptions, required permissions, and response schemas — but content is scattered across separate product APIs (Jira Platform, Jira Software, Confluence, Bitbucket) with no unified entry point
  • The API intro page provides excellent structured context for authentication, pagination, timestamps, and status codes — but error recovery guidance beyond status code descriptions is limited

What to change

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

  1. 01Add llms.txt at developer.atlassian.com covering the unified API surface across Jira, Confluence, Bitbucket, and Trello — this is the highest-impact quick win for discovery
  2. 02Add .well-known/mcp.json pointing to the official Atlassian Remote MCP Server at atlassian.com/platform/remote-mcp-server
  3. 03Create a unified API overview page that summarizes capabilities across all Atlassian products — currently an agent must discover each product API independently
  4. 04Add llms-full.txt with consolidated API documentation in markdown format
  5. 05Enhance error documentation with actionable recovery steps for common 4xx errors specific to each API operation

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_keyoauth2basic_auth✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Multiple APIs across products (Jira, Confluence, Bitbucket, Trello). OAuth 2.0 and API token auth for Cloud; basic auth for Server. JSON error responses with status codes. Rate limits documented. Cursor-based pagination with expand parameters. No idempotency keys documented.

See your own Discry Score.

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

Discry your API — free