Audit GitHub repositories for portfolio readiness, documentation quality, and basic AI-project hygiene.
Single tool with minimal schema and weak descriptions. Tool name 'audit_github_portfolio_repo' is clear and verb-prefixed, but the input schema lacks parameter descriptions entirely. The tool description (16 chars) is critically short and fails to explain WHAT the tool does, WHEN to use it, or what it returns. No output schema is documented. The implementation is functional but does not meet production-grade definition standards.
Audit a GitHub repository for portfolio readiness.
Tool description is critically short (16 chars: 'Audit a GitHub repository for portfolio readiness.'). Fails to explain what the tool returns, when to call it, or how to interpret results. LLMs cannot determine selection criteria.
Input parameter 'repository' has no description. LLMs cannot infer that it expects 'owner/repo' format without explicit guidance. Parameter descriptions are mandatory.
No output schema documented. LLMs do not know what fields the audit result contains (score, status, findings, etc.) or how to extract and use them downstream.
No error handling guidance. If repository is not found, private, or GitHub API fails, the tool returns a generic error. LLMs receive no recovery hints (e.g., 'Try a public repo' or 'Check GITHUB_TOKEN').
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 42 | 2026-07-28+ | v2 |
STDIO-only transport. Server is not remotely accessible and cannot be used by hosted MCP clients. Limits deployment to local/CLI-only scenarios.