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

Annotations already cover read-only/idempotent/non-destructive, and the description still adds substantial value: only added (+) lines are scanned, findings carry new-file line numbers and a 1-4 severity scale, and the tool never raises protocol errors but returns a structured error object that is safe to retry after fixing input. That error contract and scan-scope disclosure go well beyond the annotations.

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?

Front-loads the purpose and cost in one line, then flags, then input/output shape, then usage boundaries, then error behavior. Every sentence carries distinct information; nothing is repeated from the annotations or schema.

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?

Covers scope, alternatives, return shape, error handling, and retry safety for a single-parameter tool. With an output schema present it need not re-describe return values, and the error contract fills the remaining gap.

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 coverage is 100% so the parameter is already documented, but the description adds a concrete call example ({"diff": "<git diff output>"}) and reinforces that only '+' lines are scanned, which clarifies what the string must contain. Slight redundancy with the schema's own description keeps it below 5.

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?

States a specific verb+resource ('risk-scan a unified diff') and frames the scope as triaging a PR diff, which immediately distinguishes it from whole-file analyzers. A reader knows exactly what class of operation this is without opening the schema.

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?

Explicitly says 'Use on a unified diff, when only the change matters' and names the two whole-file alternatives (complexity_report, ai_code_smell_scan) to use instead. However, it flags 'leaked secrets' while a sibling secret_scan exists, and the description never explains when to prefer one over the other, leaving a real routing ambiguity.

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