Loading ToolBench
Context7 CLI for AI agents - fetch up-to-date library documentation
Context7 CLI exposes 2 tools with basic schemas and descriptions, but falls short of production quality. Tool names lack action verbs (search, docs are acceptable but generic). Descriptions are present but minimal (10-30 chars). Parameter descriptions exist but lack detail on constraints, formats, and dependencies. No output schema documentation. Error handling is absent from tool definitions. The server is a CLI wrapper, not an MCP server with proper tool registration, tool definitions are inferred from command-line parsing rather than explicit MCP tool registration.
Fetch docs (auto-resolves names to IDs)
Browse available libraries
Tool definitions are inferred from CLI argument parsing, not explicitly registered as MCP tools. No evidence of MCP tool registration API calls (e.g., tools/list response, tool schema declarations). This violates the MCP protocol contract.
No output schema documentation. Tools return JSON to stdout, but the response structure is not documented. LLMs cannot plan downstream operations or extract required fields without knowing what fields are returned.
Parameter descriptions lack actionable constraints. 'detail' enum is documented, but 'library' and 'name-or-id' lack format guidance. 'tokens' has no min/max bounds. LLMs cannot validate inputs without explicit constraints.
Tool descriptions are too brief (10-30 chars). 'Browse available libraries' and 'Fetch docs (auto-resolves names to IDs)' lack context on when to use each tool, what they return, and how they differ. Baseline is 194 chars.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 36 | 2026-07-28+ | v2 |
No error handling guidance. Tool definitions do not document failure modes, recovery steps, or error classification (retryable vs. fatal). Agents cannot self-correct on failures.