# Edamam — API Agent Score

> Score: 80/100 (Grade: A) | Domain: edamam.com | Rubric: 1.0.0 | Checked: October 22, 2026

Edamam scored 80/100 (A), classified "ai-ready".

[View full report](https://www.postman.com/ai/ai-ready-apis/company/edamam)
[All organizations](https://www.postman.com/ai/ai-ready-apis/llms.txt)

## Summary

- Overall: 80/100 (A)
- Classification: ai-ready

## Category Scores

- API Design: 91/100 (A+)
- Developer Experience: 58/100 (D)
- Agent Discovery: 82/100 (A)
- Agent Understanding: 86/100 (A)
- Agent Usability: 81/100 (A)

## Check Results

### API Design

- [pass] Machine-readable, versioned contract — Uses OpenAPI 3.0.3 (3.0.x; 3.1 adds JSON Schema 2020-12 alignment but is not required for full credit), a current version that agent tooling reads natively. Investigated: spec 100%, docs 100%.
- [pass] Schema coverage & depth — 7/7 (100%) public params are fully typed (no any/**kwargs). Analyzer confirms all methods have a derivable input schema. Investigated: sdk 100%, spec 67%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, sdk 100%, wellknown 50%.
- [warn] Auth declared & discoverable — The spec declares no authentication scheme, so an agent can't tell how to authenticate a request. Investigated: spec 58%, docs 58%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, spec 8%, docs 0%.

### Developer Experience

- [pass] Self-service developer portal — Signup page found at https://www.edamam.com/, but no free tier or sandbox is documented in docs/pricing, so an agent may hit a paywall. Investigated: docs 100%.
- [pass] Description completeness — Only 34% of operations and parameters have descriptions (15 of 23 ops, 2 of 61 params), leaving an agent to guess what most endpoints do. Investigated: spec 100%, sdk 0%.
- [fail] Quickstart present — No quickstart or getting-started page found at the conventional docs paths, so new developers and agents have no obvious first step. Investigated: docs 0%.
- [fail] Code samples in docs — No code samples detected across 1 sampled docs pages, so a coding agent gets no ready-to-use examples. Investigated: docs 0%.
- [fail] Changelog published — No changelog link or mention appears in the spec, so an agent can't tell what changed before something breaks. Investigated: spec 0%, docs 0%.

### Agent Discovery

- [pass] Docs reachable, not hard auth-gated — All 1 pages are publicly accessible. Investigated: docs 100%.
- [pass] Registry & SDK presence — Indexed on Context7 (borkdude/edamame, 128 snippets). Investigated: docs 100%, sdk 83%, cli 0%.
- [warn] llms.txt present, valid & comprehensive — No llms.txt found at any candidate location (https://developer.edamam.com/llms.txt, https://developer.edamam.com/docs/llms.txt). Investigated: docs 50%, sdk 0%.
- [warn] Crawlable / AEO — No sitemap found via robots.txt or /sitemap.xml on the docs host, so AI search engines have no crawl map for your docs. Investigated: wellknown 50%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — Only 2 distinct 4xx/5xx error codes are documented (plus 0 catch-all "default" responses), so an agent has limited failure branching. Investigated: docs 100%, spec 50%.
- [pass] Operation purpose clarity — Surface uses a single dominant casing convention (camelCase). Investigated: sdk 100%, spec 0%.
- [pass] Agent-navigable, token-efficient docs — All 1 pages contain server-rendered content. Investigated: docs 100%.
- [warn] Agent instructions file (AGENTS.md) — No agents.md or skill.md context file found (nice-to-have for agent operation). Investigated: sdk 50%, wellknown 0%.
- [warn] Description consistency across surfaces — Mean pairwise description similarity across 3 surfaces (spec, docs, sdk) is 16% (threshold 35% for full credit).
- [fail] Docs structured data — No JSON-LD or OpenGraph/meta tags found across 1 assessed pages (1 JS-rendered), so answer engines have nothing to cite. Investigated: docs 0%.

### Agent Usability

- [pass] Idempotency documented — Built-in retry machinery is present (grep-derived). Investigated: sdk 100%, spec 0%, docs 0%.
- [pass] Pagination documented & consistent — Pagination parameters are present on the 1 list endpoint(s), so an agent can page through results. Investigated: docs 100%, spec 75%.
- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%, spec 0%, docs 0%.
- [pass] Runnable collection with test scripts — README is present and includes a runnable quickstart. Investigated: sdk 100%, platform 0%.
- [fail] Rate-limit signaling — No rate-limit response headers are documented, so an agent can't tell when it is approaching a limit and will get throttled. Investigated: spec 0%, docs 0%.

## Executive Summary

Edamam's API program earns strong marks for design, discovery, and agent context — but two areas are holding back partner adoption: developer experience and agent understanding of operational signals. Partners and their AI agents currently land with no quickstart, no code examples, no changelog, and no structured metadata to orient them, meaning first integrations require guesswork rather than guided momentum. Prioritize building a documented, always-current onboarding surface with versioning signals and rate-limit guidance so partners can self-serve from day one.