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

Annotations only declare readOnly and openWorld; the description adds the material behavior an agent cannot infer: billing model ($0.002 USDC per successful call via x402 on Base/Solana/Arc), the fact that failed calls are not charged, that detection is pattern-based and therefore lossy, and that the response includes both redacted text and counts. Cost and failure semantics are exactly the kind of context annotations cannot carry.

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-loaded with verb and scope, then detectors, then limitations, then pricing – a sensible information ordering with no filler sentences. The detector enumeration is long but each item materially widens or narrows what the agent expects to be caught.

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?

With an output schema, annotations and a fully documented parameter, the description still adds the two things that matter – detection limits and pay-per-call cost. It stops short of stating whether the caller's text is retained or logged, which matters for a redaction tool handling secrets.

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 description coverage is 100% and the single `text` parameter already documents its 1–50000 character bound, so the schema does the work. The description does not add any semantics about the input beyond the general notion of 'text', so the baseline 3 is appropriate.

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?

Specific verb ('masks') plus a precise resource ('secrets and personal data in agent logs or chat text'), followed by an explicit enumeration of detected pattern classes (0x private keys, base58 keys, JWTs, AWS key ids, token prefixes, Luhn-valid cards, emails). No sibling tool performs PII/secret redaction, so the scope is unambiguous against the rest of the catalogue.

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 intended inputs are stated ('agent logs or chat text') and the coverage boundaries are given as explicit exclusions: it can miss unusual formats and does not detect seed phrases or names. What is missing is any redirection to an alternative tool for the out-of-scope cases, so there is clear context but no named alternatives.

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