◎ Discry Score
dhl.com
communication · API
C
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 98 (A)
Discry your API →
COMMUNICATION · RANK #19 OF 24

DHL is Needs Work to agents.

Discry independently scored how well an AI agent can discover and understand the DHL 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 · 52/100
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.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 · 76/100
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.Partial
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Fail
Token efficiencyDocs are concise enough to fit an agent context window.Partial

What we found

  • DHL's Shipment Tracking API documentation is a comprehension standout — task-oriented use cases ('Find the location of a shipment', 'Discover when a shipment will arrive') with realistic cURL and Python examples that an agent can immediately adapt
  • The downloadable OpenAPI spec (OAS3 YAML) with Postman and Bruno collections makes machine consumption straightforward, but discovery signals beyond the spec are entirely absent — no llms.txt, no AGENTS.md, no .well-known/mcp.json
  • DHL uses RFC 7807 Problem Detail for errors, which is a structured, machine-parseable format that agents can reliably parse — a positive signal for execution quality
  • An agent would not discover this API through any AI-native channel — no llms.txt, no MCP server from DHL, no GitHub presence. The only path is traditional web search leading to developer.dhl.com
  • Rate limits start at 250 calls/day with clear upgrade instructions, but the manual approval process ('Our team will review your request') creates friction for automated agent provisioning

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.dhl.com covering the API portfolio (Tracking, Shipping, Location Finder) with structured descriptions and links
  2. 02Create llms-full.txt with the complete API documentation in markdown for LLM consumption — the current Drupal-rendered pages parse poorly
  3. 03Add .well-known/mcp.json pointing to the community DHL Shipment Tracking MCP server on Smithery or build an official one
  4. 04Serve documentation pages in markdown format (Accept: text/markdown) to improve LLM comprehension — current HTML-only format loses structure on conversion
  5. 05Add AGENTS.md to a DHL developer GitHub repo with API context for coding agents

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

API key authentication via DHL-API-Key header. RESTful JSON responses with JSON-LD compatibility. Error responses use application/problem+json (RFC 7807). Rate limits well documented: 250 calls/day initial, 1 call per 5 seconds, with upgrade request process. Pagination supported. ISO 8601 date/time format. No idempotency support documented.

See your own Discry Score.

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

Discry your API — free