◎ Discry Score
vonage.com
communication · API
C
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 98 (A)
Discry your API →
COMMUNICATION · RANK #18 OF 24

Vonage is Needs Work to agents.

Discry independently scored how well an AI agent can discover and understand the Vonage 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 · 78/100
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.Pass
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.Partial
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

  • Vonage provides excellent error recovery guidance — every SMS error code includes both a description AND a specific resolution step, which is ideal for agent self-correction.
  • The developer portal has 'Copy for LLM' and 'View as Markdown' buttons on every page, showing explicit awareness of AI/agent consumption needs.
  • No llms.txt, llms-full.txt, or AGENTS.md exists despite the site being clearly AI-aware (has AI chat, LLM copy features).
  • OpenAPI specs are downloadable directly from each API reference page in both YAML and JSON formats.
  • Field naming is inconsistent between kebab-case (message-id, status-report-req) and camelCase (messageId in webhooks), which could confuse agents parsing responses.

What to change

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

  1. 01Create an llms.txt at developer.vonage.com with structured overview of SMS, Voice, Messages, and Verify APIs — the infrastructure is clearly ready given the existing 'Copy for LLM' feature.
  2. 02Add an AGENTS.md to the Vonage GitHub org covering SDK usage patterns and common multi-API workflows.
  3. 03Standardize field naming across APIs — the kebab-case/camelCase inconsistency between request params and webhook payloads is a significant agent confusion vector.
  4. 04Add dedicated multi-step workflow guides showing end-to-end flows (e.g., 'Set up SMS: create account → get number → send SMS → handle delivery receipt → process inbound').
  5. 05Publish .well-known/mcp.json given the existing Vonage-Community MCP servers on Glama.

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/secret (Basic Auth header)JWT (JSON Web Tokens)Signed requests (HMAC)✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Well-documented execution characteristics including structured error responses with numeric status codes and resolutions, throughput rate limiting, and multiple auth methods. Error codes include actionable resolution steps. 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