Agent Evaluation Harness Design Prompt

Design an evaluation harness for the agent below. Specify:
- 5 tasks of increasing difficulty (with expected outcomes).
- The metrics: success rate, avg steps, avg cost, safety violations, unnecessary-tool-call rate.
- How to detect infinite loops and reward early completion.
- A baseline to compare against (e.g., a single-tool-call agent).

Agent description: {{agent}}

Replace the {{fields}} with your own context and tighten the rules to match your domain.