# UPS — API Agent Score

> Score: 59/100 (Grade: D) | Domain: ups.com | Rubric: 1.0.0 | Checked: July 24, 2026

UPS scored 59/100 (D), classified "not-ai-ready".

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

## Summary

- Overall: 59/100 (D)
- Classification: not-ai-ready

## Category Scores

- API Design: 78/100 (B)
- Developer Experience: 44/100 (F)
- Agent Discovery: 55/100 (D)
- Agent Understanding: 81/100 (A)
- Agent Usability: 45/100 (F)

## Check Results

### API Design

- [warn] Schema coverage & depth — Only 50% of operations have documented schemas. Investigated: spec 78%, sdk 25%.
- [warn] Machine-readable, versioned contract — No info.version and no versioning scheme detected. Investigated: spec 65%, docs 30%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%.
- [warn] Auth declared & discoverable — No securitySchemes declared. Investigated: docs 50%, spec 25%, wellknown 0%.
- [pass] Example coverage — 0% example coverage. Investigated: spec 100%, sdk 100%.

### Developer Experience

- [warn] Description completeness — 6/15 operations lack a description. Investigated: sdk 60%, spec 0%.
- [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] Changelog published — No changelog URL or mention found in spec metadata. Investigated: spec 0%, docs 0%, sdk 0%.
- [skip] Quickstart present — No surface produced evidence for this capability in this run.
- [skip] Code samples in docs — No surface produced evidence for this capability in this run.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (websites/developer_ups, 51856 snippets). Investigated: docs 100%, sdk 50%, cli 0%.
- [fail] llms.txt present, valid & comprehensive — No /llms-full.txt found at the candidate origins. Investigated: docs 0%, sdk 0%.
- [fail] Crawlable / AEO — No sitemap discoverable via robots.txt or /sitemap.xml on the docs host. Investigated: wellknown 0%.
- [skip] Docs reachable, not hard auth-gated — No surface produced evidence for this capability in this run.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — No 4xx/5xx response codes (or default error response) documented anywhere in the spec. Investigated: docs 100%, spec 50%.
- [warn] Operation purpose clarity — 0% of operations are agent-inferable. Investigated: spec 85%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [skip] Agent-navigable, token-efficient docs — No surface produced evidence for this capability in this run.
- [skip] Docs structured data — No surface produced evidence for this capability in this run.
- [skip] Description consistency across surfaces — Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [warn] Sandbox separation — No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%, spec 0%, docs 0%.
- [warn] Runnable collection with test scripts — No test scripts found in the workspace's collections. Investigated: platform 50%.
- [fail] Idempotency documented — 0% of mutating operations document idempotency. Investigated: spec 0%, docs 0%, sdk 0%.
- [fail] Rate-limit signaling — No rate-limit response headers documented. Investigated: spec 0%, docs 0%.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

UPS's API design foundation is solid, and agent understanding is largely strong — but the partner program has critical gaps in discoverability, onboarding, and operational reliability that will block both human partners and AI agents before they ever make a first call. The highest priorities are establishing a self-service front door with machine-readable discovery signals, and documenting the operational contracts (idempotency, rate-limiting, and change history) that agents and integrators depend on to build trustworthy workflows.