◎ Discry Score
box.com
productivity · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 92 (A)
Discry your API →
PRODUCTIVITY · RANK #4 OF 24

Box is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Box 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 · 76/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Pass
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Partial
llms-full.txtA full-text bundle agents can load in one request.Pass
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 · 91/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Pass
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.Partial

What we found

  • Box has exceptional comprehension quality: code examples in 5 languages (TypeScript, Python, .NET, Swift, Java) for every endpoint, task-oriented descriptions, and 'Before you start' prerequisite sections that guide agents through multi-step workflows
  • The OpenAPI spec is well-maintained in a dedicated box/box-openapi repo with versioned specifications (pre-2025 and 2025.0+) — enabling reliable agent auto-discovery and code generation
  • Documentation is fully available as markdown (.md URLs in llms.txt) with a comprehensive llms-full.txt at 3.9MB containing 5,314 sections — thorough but right-sized compared to Snowflake's 52MB
  • Box has invested in AI agent infrastructure (AI Studio, Agent Skills, Remote MCP Server) with dedicated developer documentation for building agent integrations — reflecting a deliberate agent-first product strategy
  • No AGENTS.md found in Box GitHub repositories despite having a Box Developer Community GitHub org — a gap for coding agents working with Box SDKs

What to change

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

  1. 01Add AGENTS.md to box/box-python-sdk, box/box-node-sdk, and box/box-openapi repos with coding agent guidance
  2. 02Add .well-known/mcp.json at developer.box.com pointing to the official Box Remote MCP Server
  3. 03Create a focused llms.txt under 50KB covering core API capabilities — the current 134KB covers all docs including AI Studio, events, and admin guides
  4. 04Enhance error documentation with actionable recovery steps beyond status code descriptions

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.

oauth2jwtclient_credentialsdeveloper_token✓ Error format documented✓ Rate limits documented✓ Pagination documented✓ Idempotency documented

Comprehensive REST API with versioning (2025.0+). OAuth 2.0, JWT, client credentials, and developer tokens for auth. JSON error responses. Rate limits documented. Both marker-based and offset-based pagination documented. Idempotency supported via consistency headers.

See your own Discry Score.

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

Discry your API — free