redact_pii

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

The description discloses the return structure (verdict, severity, findings, redacted payload) and mentions producing an audit artifact. With no annotations, it carries the burden well, though it does not specify authorization needs or logging behavior.

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 concise with three sentences plus a parenthetical, each adding value. It front-loads the purpose and usage, then details returns and references, without extraneous text.

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?

For a tool with two parameters and no output schema, the description covers purpose, usage, return values, and a reference. It lacks explanation of the context parameter, which is a minor gap, but overall is reasonably complete.

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 0%, so the description must compensate. It explains 'payload' as the target content, but the optional 'context' parameter is not described at all, leaving the agent uncertain about its purpose or expected format.

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 detects personal data and secrets in a payload, listing specific categories (PII, secrets) and providing a use case (before transmitting outside trust boundary). It differentiates from siblings like detect_injection by focusing on sensitive-data leakage.

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 advises using the tool before transmitting text outside a trust boundary, providing clear context. It does not explicitly exclude scenarios or name alternatives, but the purpose is distinct enough among siblings.

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