anonymize_cv

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

With no annotations provided, the description must fully disclose behavior. It mentions stripping PII and generating a 'structured audit trail' with 'compliance-friendly evidence packs,' adding useful context. Yet it does not explain the return value, side effects, or input format prerequisites, leaving critical behavioral gaps.

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 the action and lists relevant details. However, the tail 'matching FormaCV's anonymization story on every plan, including compliance-friendly evidence packs' is marketing language that adds no operational value for an AI agent, reducing conciseness.

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 no annotations, no output schema, and a nested input object, the description is incomplete. It fails to explain how to pass the CV (url/base64), what the tool returns, or how audit_log affects output. The sibling tools provide some context, but the description alone is insufficient for correct invocation.

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?

The schema has no field descriptions (0% coverage), so the description must compensate. It lists exact field names that match the fields_to_strip enum, and 'audit trail' relates to audit_log. However, the required cv parameter (object with source and data) is completely unaddressed, leaving a major usability gap.

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 opens with 'Strip personally identifying details (name, email, phone, photo, address, company names)' which clearly states the action and resource. It further specifies the purpose 'for blind client submissions,' distinguishing it from sibling tools like format_cv or tailor_cv.

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?

'For blind client submissions' provides a clear context for when to use this tool, implying a specific use case. However, it does not explicitly name alternatives or exclusions, stopping short of full guidance for tool selection among siblings.

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