run_autoresearch

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

The description details the iterative, metric-driven nature and the requirement for checks, adding behavioral context beyond the destructiveHint annotation. It explains what the loop does and how decisions are made, which is valuable for an agent.

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?

A single, packed sentence that front-loads the key action and steps. It is not overly verbose, though it could be broken into two sentences for readability. Still efficient and clear.

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?

Given the complexity (9 parameters, no output schema, destructive hint), the description provides a high-level process but lacks details on return values, per-parameter behavior, and error handling. Adequate but not thorough.

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 coverage is 100%, so baseline is 3. The description does not add parameter-specific meaning beyond the schema; it only describes the overall process. No enhancement or compensation is needed.

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 clearly states the tool runs a bounded metric-improvement loop with specific steps: baseline measurement, hypothesis testing, primary and holdout checks, candidate mutation with proof. This distinguishes it from sibling tools like run_harness or run_self_distill, which serve different purposes.

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?

No explicit guidance on when to use this tool versus alternatives. Siblings include many optimization and feedback tools, but the description does not provide context or exclusions for appropriate usage.

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