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

Annotations already declare read-only/idempotent/non-destructive, and the description adds what they cannot: raw values are withheld unless reveal:true, the redaction style options, the 200 KB limit, and the per-call price. A mutation-free but paid, quota-bearing tool is disclosed thoroughly.

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 capability, then validation detail, then output shape, then operational constraints (limit, price, endpoint). It is dense and long-ish for one paragraph, but each clause carries distinct information.

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?

There is no output schema, and the description compensates by describing the return payload precisely: per-type counts, findings with code-point offsets, confidence, masked values, and a redacted copy. Combined with limits and pricing, an agent has everything needed to call it 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 description coverage is 100%, so all four parameters are already documented. The description restates reveal:true and the label/mask styles with an example ([EMAIL_1], j***@example.com) but adds little semantics beyond the schema; baseline 3 applies.

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?

Opens with a specific verb+resource (detect and redact PII in text) and then enumerates exactly which entity classes it handles and which validation rules it applies (Luhn, SSA, mod-97). This clearly separates it from siblings like email_validate, contact_extract, or prompt_injection_scan.

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 concrete operating context: fully offline, 200 KB text cap, paid at $0.01 per successful call, and an alternate HTTPS endpoint. It does not explicitly say when to prefer this over email_validate or contact_extract, so it stops short of full alternative routing.

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