evaluate-mcp-tool-adoption
Evaluate MCP Tool Adoption
Evaluate an agent-facing tool as a routing surface, not as a call-count target. Distinguish availability, discovery, selection, and execution before changing server instructions, tool metadata, or the operation contract. Load this skill only for the evaluator; never enable it in an agent-under-test configuration.
Use harbor-benchmarks for a Harbor task or verifier change and
verifier-evaluations for its mathematical verifier. This skill owns only the
adoption diagnosis and its evidence boundary.
Freeze the question
For a controlled comparison, write one falsifiable question, such as “does server-level guidance cause an agent to inspect a matching operation when the ordinary prompt does not?” Keep the model, model version, reasoning effort, client version, Jacobian revision, image digest, task digest, MCP configuration, egress/proxy state, attempt count, and budgets fixed across comparable arms.