BackTool
Agent-Readiness Linter
A rule-based scorecard for API specs, designed around the patterns LLM agents actually need — error shape, idempotency, retryability, scoped auth, and explicit pagination.
Paste an OpenAPI spec (JSON or YAML) and the linter scores it against the patterns that matter when AI agents are calling your backend — error shape, idempotency, retryability, scoped auth, pagination, and more. Everything runs in your browser; nothing is sent anywhere.
InputJSON or YAML · stays local
Report
Paste a spec on the left and hit Run Linter to see the scorecard.