Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description explicitly discloses that the tool uses the user's API keys (cost implications), may take several minutes (time expectation), and mutates the system prompt (state-changing behavior). This is substantial context that helps the agent set expectations and assess side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded with the primary purpose, followed by the process, return value, and critical caveats. Each sentence adds unique information with no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with no output schema, the description effectively communicates the core behavior, side effects (API key usage, time), and return value. It could mention prerequisites like the agent and suite needing to exist, but these are implied by the parameter names and the optimization context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema covers 100% of parameters with clear descriptions, so the description does not need to elaborate. The schema already explains agent_id, suite_id, target_score, max_iterations, and max_token_budget. The description adds no additional semantic meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Run AutoTune optimization') with a clear resource ('an agent'), and explains the iterative mutation process. It is distinct from siblings like run_grading or grade_prompt by focusing on automated optimization, not just grading.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it (for optimizing an agent's prompt via AutoTune), but provides no explicit exclusions or comparisons to alternatives. It does not mention that run_grading or grade_prompt might be better for simple grading tasks, leaving the agent to infer the appropriate context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.