MCP Server for AST static analysis to identify prohibited imports and syscalls in Python code
Single tool with minimal definition quality. Tool name 'audit_code_safety' lacks action verb clarity (should be 'audit_code' or 'check_code_safety'). Description is present but generic (58 chars, below 100-char minimum for clarity). Input schema exists but parameter 'code' lacks description entirely, violates critical rule that every parameter needs a description. No output schema documented. No error handling guidance. No parameter constraints or validation hints. Tool does not follow composition patterns for agent-friendly design.
Perform AST static analysis to identify prohibited imports and syscalls.
Parameter 'code' has no description in schema. LLMs cannot infer what format, length, or content is expected.
No output schema documented. LLMs cannot plan downstream actions or extract violation details reliably.
Tool description is generic (58 chars). Does not explain WHEN to use it, WHAT it returns, or HOW to interpret violations.
No error handling guidance. SyntaxError returns a violations array, but LLM has no instruction on how to recover or retry.
Tool name 'audit_code_safety' is ambiguous. Does it audit, check, validate, or scan? Verb should be clearer (e.g., 'check_code_safety' or 'audit_code').
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 39 | 2026-07-28+ | v2 |