Atlassianatlassian.com

ScoredJul 24, 2026, 05:46 AM

Atlassian's API design is a clear strength — the contract is machine-readable, well-shaped, and auth is properly covered — giving partners a solid foundation to build on. md instruction file, no structured data in docs, and no idempotency guidance, leaving AI agents without the context they need to integrate safely and autonomously.

API DesignA clean, typed, well-governed API contract agents can reason about2 pass3 warn0 fail84A
SignalPointsFindingsRationale
passSchema coverage & depthvia sdk25/25package.json "types" → lib/index. Investigated: sdk 100%, spec 47%.Typed, complete request/response schemas are what make agent function-calling possible.
warnMachine-readable, versioned contractvia spec18.8/25info.version="1001.0.0-SNAPSHOT-b5920d1eaef179a2bd7f107d8da95822cab568b5" set but no versioning scheme (URL / header / media type) detected. Investigated: spec 75%, docs 50%.A current OpenAPI version with a declared versioning scheme lets agents reason about the contract.
warnAuth declared & discoverablevia spec17.5/251 OAuth2/OIDC scheme(s) defined but no scopes documented. Investigated: spec 70%, docs 60%, wellknown 0%.Agents can only authenticate when auth is declared, scoped, and discoverable.
passSecurity & governance hygienevia spec15/15No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 100%.No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel.
warnExample coveragevia sdk5/10README is present but has no runnable quickstart. Investigated: sdk 50%, spec 0%, docs 0%.Examples carry shape semantics schemas under-specify — for humans and agents alike.
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples3 pass1 warn1 fail75B
SignalPointsFindingsRationale
passSelf-service developer portalvia docs29/29Signup page at https://www.atlassian.com/; no free-tier language detected in docs/pricing. Investigated: docs 100%.Self-serve key/account creation is the fast first call for partners, with no sales gate.
passDescription completenessvia spec15/1596% of operations + parameters have substantive descriptions. Investigated: spec 100%.Complete descriptions are the context humans and agents need to use endpoints.
passChangelog publishedvia sdk13/13Newest official SDK activity 10 day(s) ago. Investigated: sdk 100%, spec 0%, docs 0%.A published changelog lets partners track changes without surprise.
warnQuickstart presentvia docs12.5/25Quickstart page reachable (3 variants scanned starting at https://developer.atlassian.com/?utm_source=%2Fgetting-started&utm_medium=301) but no runnable code sample detected in HTML or .md variant. Investigated: docs 50%.A quickstart is the fastest path from landing page to first successful call.
failCode samples in docsvia docs0/18No detectable code samples across 9 sampled docs pages. Investigated: docs 0%.Multi-language samples shorten time-to-first-call.
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs1 pass3 warn0 fail69C
SignalPointsFindingsRationale
passRegistry & SDK presencevia docs28/28Indexed on Context7 (websites/developer_atlassian_platform_forge, 10616 snippets). Investigated: docs 100%, cli 100%, mcp 100%, sdk 67%, wellknown 0%.Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look.
warnDocs reachable, not hard auth-gatedvia docs15/3015 of 50 sampled pages return 200 for non-existent URLs (soft 404). Investigated: docs 50%.Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics.
warnllms.txt present, valid & comprehensivevia docs10/30No llms.txt found at any candidate location (https://developer.atlassian.com/llms.txt, https://developer.atlassian.com/docs/llms.txt). Investigated: docs 33%, sdk 0%.A valid, comprehensive llms.txt is the machine-readable entry point for agents.
warnCrawlable / AEOvia wellknown9/12Sitemap present (65 entries) but carries no lastmod values. Investigated: wellknown 75%.Bots allowed plus a fresh sitemap make docs findable by agent crawlers.
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs1 pass3 warn2 fail69C
SignalPointsFindingsRationale
passMachine-readable errors (RFC 9457)via docs28/288 distinct 4xx/5xx response codes documented. Investigated: docs 100%, spec 50%.RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens.
warnOperation purpose clarityvia spec20/2531% of operations are agent-inferable. Investigated: spec 80%.Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice.
warnAgent-navigable, token-efficient docsvia docs12.2/223 of 50 sampled pages appear to be client-side rendered SPA shells (root detected); agents using HTTP fetches will see no content. Investigated: docs 56%.Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly.
warnDescription consistency across surfaces0.8/7Mean pairwise description similarity across 3 surfaces (spec, docs, sdk) is 4% (threshold 35% for full credit).Every surface tells the same story about what the product is.
failAgent instructions file (AGENTS.md)via wellknown0/10No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.An AGENTS.md gives coding agents explicit setup, auth, and usage instructions to interpret and operate the API — beyond llms.txt's link index.
failDocs structured datavia docs0/8Neither JSON-LD nor OpenGraph/meta tags detected across 1 assessed pages (1 JS-rendered). Investigated: docs 0%.Structured data (JSON-LD/schema.org) on docs pages gives agents an unambiguous parse target and is what answer engines cite. Detected on the JS-rendered head (Firecrawl) for a bounded page budget, so JS-injected JSON-LD is now caught; pages we can't render are excluded rather than failed.
Agent UsabilityAgents have the context to use your APIs reliably, not just find them1 pass2 warn2 fail53D
SignalPointsFindingsRationale
passPagination documented & consistentvia docs22/22pagination documented in the docs site at https://www.atlassian.com/software/jira/dev. Investigated: docs 100%, spec 75%.Consistent, documented pagination lets agents traverse collections.
warnSandbox separationvia sdk10/20No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%, spec 0%, docs 0%.An isolated environment lets agents exercise destructive operations safely.
warnRate-limit signalingvia spec4.4/22No rate-limit response headers documented. Investigated: spec 20%, docs 20%.Machine-readable rate-limit headers let agents throttle adaptively.
failIdempotency documentedvia spec0/270% of mutating operations document idempotency. Investigated: spec 0%, docs 0%, sdk 0%.Documented idempotency lets agents retry safely.
failRunnable collection with test scriptsvia platform0/9No test scripts found in the workspace's collections. Investigated: platform 0%.A public, maintained collection with assertions is runnable truth agents validate against.
Resources Discovered

The public resources we found for Atlassian — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.

Agent hintsContext7 (10,616)
APIs analyzed5The Jira Cloud platform REST API, Bitbucket API, The Confluence Cloud REST API, Jira Software Cloud API, Service Management Public REST API
Want to improve your results?