redact

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: results are 'stable placeholders,' the tool is 'Deterministic,' and 'the mapping is returned so YOU reveal replies locally.' That reveal-via-mapping detail is exactly the kind of non-obvious behavior an agent needs. It omits auth/rate-limit context, but that is minor for a pure transform.

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 core action is front-loaded, which is good, but the description is long and rambles into deployment advice ('the strip belongs at your edge'). The '[CHECK · internal]' marker is unexplained noise and adds nothing for an agent.

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 single-parameter, no-output-schema tool, the description covers purpose, usage timing, determinism, the returned mapping, and a sibling pairing. It is largely self-sufficient; only the exact shape of the mapping and the input length cap are left implicit.

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% for the single 'text' parameter, so the description must compensate. It confirms the input is text to be stripped but adds no format, size, or requiredness detail beyond the schema (e.g. the 4000-char cap is only in the schema). It minimally compensates rather than fully.

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 and target: 'Strip PII (emails, SSNs, credit cards, IPs, URLs) from text to stable placeholders.' This is unambiguous and clearly differentiates the tool from every sibling, none of which perform redaction. The unexplained '[CHECK · internal]' prefix and the dense phrasing keep it just short of a clean 5.

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?

Gives real usage context: run it 'before you pass it onward' and 'pair with verify for a receipt,' which names an actual sibling. It also steers toward a LOCAL/sovereign engine for genuine privacy. It stops short of explicit when-not-to-use or stated alternatives to this tool itself.

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