Fast code intelligence engine for AI coding agents — single static binary MCP server
Single tool 'index_repository' has a basic description but lacks critical detail. Input schema visible with two parameters (repo_path, mode) but both lack descriptions, violating the requirement that every parameter must explain what it controls. No output schema documented. Description is 87 chars (below the 194-char baseline for A+ tools) and does not explain WHEN to use this tool, what it returns, or whether it has side effects. The tool modifies state (builds a graph) but the description does not declare this. No error handling guidance. Tool name is verb-noun compliant but the schema is incomplete.
Index a codebase repository to build a code intelligence graph
Missing parameter descriptions: 'repo_path' and 'mode' have no descriptions. LLMs cannot infer what 'mode' values are valid or what 'repo_path' format is expected.
No output schema documented. LLMs cannot plan downstream operations or extract results without knowing what fields the tool returns.
Tool description (87 chars) lacks WHEN/WHY guidance and does not declare state modification. Description should explain: What does 'build a code intelligence graph' mean? What does it return? Is this idempotent? Can it be retried?
'mode' parameter has no enum constraint or description. LLMs will guess at valid values ('full', 'partial', 'incremental'?) instead of being told explicitly.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | <=2025-11-25 | v2 |
No error handling guidance. If indexing fails (e.g., invalid repo path, permission denied), the tool provides no recovery hints for the LLM.