Automated MCP Testing: Using Composable Goose Recipes to Validate Tool Metadata
· 15 min read
When building Model Context Protocol (MCP) servers, most development focuses on tool functionality, ensuring tools execute and return expected results. But just as critical is the quality of tool metadata: descriptions, tooltips, and input schemas. These elements form the "interface language" between tools and AI agents like Goose.
Yet metadata often goes untested. This can break tool discovery and silently degrade agent behavior. In this post, we’ll show how to automate metadata validation using composable Goose recipes, turning manual QA into modular, repeatable workflows that:
- Validate tool discoverability and parameter accuracy
- Detect regressions early
- Safely reduce token usage
All while maintaining the quality that AI agents depend on.