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

Beyond the annotations, it discloses important behavior: invalid input never raises a protocol error and instead returns an error object, retry is safe after correction, and the result should be interpreted as a confidence signal rather than definitive proof.

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 front-loaded with purpose and concrete smell categories, then moves into usage and error behavior. It is efficient, though the example input/output overlaps with structured schema information and the read-only/idempotent note repeats annotations.

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 presence of an output schema, complete input schema, and rich annotations, the description provides everything needed: purpose, usage boundaries, interpretation caveat, and error handling behavior.

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?

Schema description coverage is 100% and the single code parameter is already well documented in the schema. The description adds a typical input shape but does not add substantive 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 and resource: flagging AI code smells in a source file. It lists concrete smell categories and explicitly differentiates from the sibling review_diff by saying it should not be used on a diff.

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?

It gives clear when-to-use guidance (full source file suspected of unreviewed machine authorship), an explicit when-not-to-use alternative (review_diff for diffs), and a caveat that the result is a signal rather than proof.

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