You are designing an MCP tool. Capability to expose: {{capability_description}}
Inputs it needs: {{inputs_description}}
What it returns: {{outputs_description}}

Produce:
1. A tool name (snake_case, verb-first) and a one-sentence description written for a model deciding whether to call it.
2. A JSON Schema for the input parameters, marking required fields and giving each a description a model can act on.
3. The output shape (fields and types), including how errors are represented.
4. One example call and one example response.
5. A note on what this tool must NOT be used for, if its name/description alone could be misread.