# Paperpal — API Agent Score

> Score: 58/100 (Grade: D) | Domain: paperpal.com | Rubric: 1.0.0 | Checked: August 17, 2026

Paperpal scored 58/100 (D), classified "not-ai-ready".

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

## Summary

- Overall: 58/100 (D)
- Classification: not-ai-ready

## Category Scores

- API Design: 55/100 (D)
- Developer Experience: 55/100 (D)
- Agent Discovery: 65/100 (C)
- Agent Understanding: 68/100 (C)
- Agent Usability: 48/100 (F)

## Check Results

### API Design

- [pass] Security & governance hygiene — Code is formatter-clean with zero linter errors and zero style warnings. Investigated: sdk 100%, wellknown 0%.
- [warn] Example coverage — README is present but has no runnable quickstart. Investigated: sdk 50%, docs 0%.
- [fail] Schema coverage & depth — no py.typed marker (PEP 561). Investigated: sdk 0%.
- [skip] Machine-readable, versioned contract — No surface produced evidence for this capability in this run.
- [skip] Auth declared & discoverable — No surface produced evidence for this capability in this run.

### Developer Experience

- [pass] Self-service developer portal — Self-service signup available at https://sso.editage.com/signup?continue=https%3A%2F%2Fapp.editage.com, with a free tier or sandbox documented — an agent can onboard without contacting sales. Investigated: docs 100%.
- [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 20 sampled docs pages, so a coding agent gets no ready-to-use examples. Investigated: docs 0%.
- [skip] Description completeness — No surface produced evidence for this capability in this run.
- [skip] Changelog published — No surface produced evidence for this capability in this run.

### Agent Discovery

- [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 — No llms.txt directive found in HTML of any of 50 sampled pages. Investigated: docs 56%, sdk 0%.
- [warn] Crawlable / AEO — Sitemap has lastmod on only 100% of entries, or its newest entry is over 90 days old. Investigated: wellknown 75%.
- [warn] Registry & SDK presence — No MCP server, tool manifest, or list-tools capability is discoverable (server entrypoint: absent, tool manifest: unknown, list-tools: unknown). Investigated: sdk 25%, docs 0%, cli 0%.

### Agent Understanding

- [pass] Operation purpose clarity — Surface uses a single dominant casing convention (snake_case). Investigated: sdk 100%.
- [warn] Agent-navigable, token-efficient docs — No sampled pages support .md URLs (0/50 tested). Investigated: docs 81%.
- [pass] Docs structured data — Machine-readable JSON-LD Article markup on 18 of 20 assessed pages (90%), with dateModified present. 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%.
- [fail] Machine-readable errors (RFC 9457) — No single common SDK base error class was found; errors do not share one root. Investigated: sdk 0%.
- [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%.
- [warn] Runnable collection with test scripts — README is present but has no runnable quickstart. Investigated: sdk 50%, platform 0%.
- [fail] Idempotency documented — No built-in retry machinery was found; transient failures are not retried. Investigated: sdk 0%.
- [skip] Rate-limit signaling — No surface produced evidence for this capability in this run.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

Paperpal's API program shows strength in agent discovery infrastructure but has critical gaps in two areas that directly block partner and agent adoption: the SDK lacks the type-safety and error-handling foundations that modern integrations depend on, and the developer documentation provides no quickstart or code examples — meaning partners and their AI agents have no obvious first step and no ready-to-use patterns to build from. The highest-priority work is establishing a reliable, self-serve onboarding path with runnable examples, followed by hardening the SDK's type contracts and error semantics so agents can integrate with confidence.