# Retool — API Agent Score

> Score: 64/100 (Grade: C) | Domain: retool.com | Rubric: 1.0.0 | Checked: July 24, 2026

Retool scored 64/100 (C), classified "partially-ready".

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

## Summary

- Overall: 64/100 (C)
- Classification: partially-ready

## Category Scores

- API Design: 93/100 (A+)
- Developer Experience: 57/100 (D)
- Agent Discovery: 76/100 (B)
- Agent Understanding: 58/100 (D)
- Agent Usability: 46/100 (F)

## Check Results

### API Design

- [pass] Machine-readable, versioned contract — Versioning declared (info.version="4.29.0") and url-versioning detected. Investigated: spec 100%, docs 100%.
- [pass] Auth declared & discoverable — Authentication required (global or on every operation). Investigated: spec 100%, docs 100%.
- [warn] Schema coverage & depth — 83% of operations have documented schemas (target 95%+). Investigated: spec 67%, sdk 0%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%.
- [pass] Example coverage — Code samples present on 7/20 pages across 2 language(s); broader multi-language coverage missing. Investigated: docs 100%, spec 0%, sdk 0%.

### Developer Experience

- [pass] Code samples in docs — Code samples present on 7/20 pages across 2 language(s); broader multi-language coverage missing. Investigated: docs 100%.
- [pass] Changelog published — changelog documented in the docs site at https://docs.retool.com/changelog. Investigated: spec 100%, docs 100%, sdk 100%.
- [warn] Quickstart present — Quickstart page reachable (4 variants scanned starting at https://docs.retool.com/) but no runnable code sample detected in HTML or .md variant. Investigated: docs 50%.
- [fail] Self-service developer portal — No signup page detected across conventional paths (/signup, /sign-up, /register, /get-started, /console/signup, /dashboard/signup, /try, /try-free, /free, /free-trial, /start, /start-free). Investigated: docs 0%.
- [fail] Description completeness — 50% description completeness. Investigated: spec 0%.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (websites/retool, 19317 snippets). Investigated: docs 100%, sdk 50%, cli 0%, mcp 0%, wellknown 0%.
- [warn] Docs reachable, not hard auth-gated — Server ignores Accept: text/markdown header (0/50 sampled pages return markdown). Investigated: docs 75%.
- [warn] llms.txt present, valid & comprehensive — llms.txt covers 837/1581 sitemap doc pages (53%); 744 missing; 290 llms.txt links not in sitemap (may indicate stale links or incomplete sitemap). Investigated: docs 38%.
- [warn] Crawlable / AEO — Sitemap present (1616 entries) but carries no lastmod values. Investigated: wellknown 75%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — 7 distinct 4xx/5xx response codes documented. Investigated: docs 100%, spec 50%.
- [warn] Agent-navigable, token-efficient docs — 3 of 40 pages have substantive content differences between markdown and HTML (avg 6% missing). Investigated: docs 61%.
- [fail] Operation purpose clarity — 0% of operations are agent-inferable. Investigated: spec 0%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [fail] Docs structured data — Neither JSON-LD nor OpenGraph/meta tags detected across 9 sampled pages — likely a CSR-only docs site. Investigated: docs 0%.
- [skip] Description consistency across surfaces — Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [pass] Pagination documented & consistent — Pagination params detected on 28 list endpoint(s). Investigated: spec 100%, docs 100%.
- [fail] Idempotency documented — 0% of mutating operations document idempotency. Investigated: spec 0%, docs 0%.
- [fail] Rate-limit signaling — No rate-limit response headers documented. Investigated: spec 0%, docs 0%.
- [fail] Sandbox separation — No sandbox/test server declared across 1 server entries; no test-key prefixes documented. Investigated: spec 0%, docs 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.

## Executive Summary

Retool's API design is a clear strength — the schema and contract surface is solid, giving partners a reliable foundation to build against. The weakest areas are agent usability and agent understanding: partners and their AI agents currently lack the runnable examples, sandbox separation, idempotency guidance, and machine-readable context they need to integrate confidently and quickly. Closing these gaps — starting with executable, trustworthy integration artifacts and then layering in richer semantic documentation — will meaningfully accelerate partner time-to-value and reduce the support burden on your team.