PageAudit exposes a single tool 'audit' with minimal definition quality. The tool name lacks a clear action verb (should be 'audit_page' or 'run_page_audit'). Description is extremely brief (11 chars: 'Audit a page'), below the 20-char minimum for actionable guidance. Input schema is present but sparse: only 'url' parameter with a basic string type and minimal description. No output schema is documented, LLMs cannot predict what fields the response contains or how to chain results. No error handling guidance, no pagination support, no parameter constraints (e.g., valid URL format).
Audit a page
Tool description is critically short (11 chars). Must explain WHAT the tool does, WHEN to use it, and what it returns. Current description 'Audit a page' provides no actionable context for LLM selection.
No output schema documented. LLMs cannot predict response structure, fields, or data types. Must document what 'report' contains (keys, types, nested objects).
Tool name 'audit' lacks action verb. Should be 'audit_page' or 'run_page_audit' to clearly signal the action. Bare noun names reduce LLM clarity.
URL parameter has no format constraint or validation guidance. Should specify valid URL format (http/https), length limits, and what happens if URL is invalid or unreachable.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 27 | 2026-07-28+ | v2 |
No error handling guidance. If audit fails (timeout, invalid URL, network error), LLM has no recovery path. Must document error categories and next steps.