◎ Discry Score
adobe.com
devtools · API
D
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 96 (A)
Discry your API →
DEVTOOLS · RANK #30 OF 39

Adobe is Poor to agents.

Discry independently scored how well an AI agent can discover and understand the Adobe 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 · 53/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Partial
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.Partial
Capability boundariesClear limits — what the API can and cannot do.Partial
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.Fail

What we found

  • An agent searching for Adobe APIs would find AGENTS.md files in multiple AEM repos and OpenAPI specs across products, showing strong agent-awareness for Adobe Experience Manager specifically
  • The developer portal at developer.adobe.com returns 404 for /llms.txt despite being a massive multi-product developer ecosystem
  • Adobe blocks no AI bots in robots.txt, signaling openness to AI consumption of developer content
  • MCP servers exist for Photoshop, Illustrator, Premiere Pro, and AEP on community registries, though none are officially maintained by Adobe
  • Documentation is fragmented across products (AEM, Creative Cloud, Document Services) making agent discovery inconsistent

What to change

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

  1. 01Add llms.txt and llms-full.txt to developer.adobe.com covering the unified API ecosystem
  2. 02Create a centralized OpenAPI spec index page rather than scattered per-product specs
  3. 03Add .well-known/mcp.json pointing to the official Adobe Skills framework
  4. 04Consolidate developer documentation into a consistent format across all Adobe products
  5. 05Create a single AGENTS.md at the org level covering the full developer platform

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

Adobe documents OAuth2, API key, and JWT auth across its various APIs. Error formats vary by product. Rate limits documented per product. Cursor-based pagination used in most APIs.

See your own Discry Score.

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

Discry your API — free