Loading ToolBench
Visualize code relationships, dependencies, and quality metrics via MCP tools
Three tools with minimal documentation. All have descriptions (10-50 chars, below the 194-char baseline), no visible input parameter descriptions, and no documented output schemas. Tool names lack action verbs (map, quality, assess_change are vague). No evidence of parameter validation, error handling guidance, or composition patterns. Schemas appear to exist in source but are not visible in provided code excerpts, preventing full assessment.
Assess the impact and quality implications of code changes
Visualize code relationships and dependencies for a given path
Analyze code quality metrics and identify code smells for a given path
Tool names lack action verbs. 'map', 'quality', 'assess_change' do not start with clear verbs (get_, create_, analyze_, etc.). LLMs cannot infer intent from these names alone.
Descriptions are too short (10-50 chars vs. 194-char baseline). 'Visualize code relationships...' and 'Analyze code quality...' lack context on WHEN to use each tool, what they return, and how they differ.
No visible parameter descriptions. The 'path' parameter in all three tools has a description in the schema, but no guidance on format, constraints, or whether it accepts files, directories, or both.
No documented output schemas. LLMs cannot plan downstream calls or extract results without knowing what fields each tool returns.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 29 | 2026-07-28+ | v2 |
No error handling guidance. If a path is invalid, does not exist, or is unreadable, what error is returned? How should the LLM recover?