tastewise/mcp-whichtool
Does the model pick the right tool? Tool-routing tests for your MCP server: run them on Claude and OpenAI models, see where each request lands, and fix the descriptions that lose.
GitHub repository with 13 stars and 0 forks.
Language: TypeScript
Topics: ai-agents, anthropic, claude, cli, developer-tools, evals, function-calling, github-actions, llm, llm-evaluation