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

Annotations already provide readOnlyHint=true and idempotentHint=true. The description reinforces these by stating 'Every call is read-only and idempotent.' It adds valuable context beyond annotations: error handling (returns error objects instead of protocol errors), licensing (PREMIUM), and retry safety. No contradictions. Minor gap: does not describe rate limits or specific authentication needs.

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 efficiently structured: first sentence states purpose, then lists checks, provides input/output example, usage guidance, error handling, and idempotency statement. Every sentence adds value with no repetition or fluff. Front-loaded with the core action.

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 tool has only one parameter, full schema coverage, annotations covering idempotency and read-only, and an output schema exists (though not provided in full), the description compensates by showing the output shape. It also covers licensing, error handling, and usage boundaries. No obvious gaps for an agent to select and invoke correctly.

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% with a single parameter 'code' described as 'Full source text to audit...'. The description adds significant meaning beyond the schema by providing an example input/output format ({'code': '<file contents>'}) and showing the expected return structure with fields like issues, findings, owasp_note. This helps the agent understand how to construct the input and interpret results, which is not in the schema alone.

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 an OWASP-oriented security pass on a source file, lists specific checks (injection, auth, crypto, etc.), and differentiates from sibling 'complexity_report' by specifying it is not for style or structure. This provides a specific verb+resource with clear scope.

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 explicitly says 'Use on one source file when vulnerabilities are the question' and warns 'Not for style or structure (complexity_report)' and 'never a substitute for a security professional on high-risk code.' It also explains error behavior and retry safety. However, it does not mention alternative siblings like secret_scan or ai_code_smell_scan, leaving some gaps in tool comparison.

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