Single tool 'search_code' has a basic schema with two parameters (query, limit) but lacks critical documentation. The tool description is minimal (18 chars: 'Search the codebase.'), below the 20-char floor for meaningful LLM guidance. No parameter descriptions are visible in the schema, violating the requirement that every parameter must explain what it controls. The input schema shows types (string, number) but no descriptions, constraints, or usage guidance. No output schema is documented. The tool definition appears to be inferred from example code rather than explicitly registered with full metadata. This server is a testing/contract-verification framework (mcp-pact), not a production MCP server, which explains the minimal tool surface.

• Expand tool description to 50 - 150 characters explaining WHAT the tool does, WHEN to use it, and what it returns. Example: 'Search the codebase for code snippets, functions, or classes matching a query. Returns up to 20 results with file paths and line numbers. Use this to explore the codebase before making changes.'
• Add descriptions to all parameters. For 'query': 'The search term or regex pattern to find in code (required, 1 - 500 chars).' For 'limit': 'Maximum number of results to return (1 - 100, default 20).'
• Document the output schema with field names, types, and descriptions. Example: {results: [{file: string, line: number, snippet: string, match_type: enum}], total_matches: number, has_more: boolean}
• Add constraints to 'limit' parameter: minimum 1, maximum 100, default 20. Prevent LLMs from requesting unreasonable result sets.
• Verify tool is explicitly registered in the MCP server code with full schema, not inferred from examples. Provide the actual tool registration code for validation.