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

Goes well beyond readOnlyHint/openWorldHint: discloses the 50-entity cap, that results are substrings of the redacted text, that source PII is redacted first, and the billing model including that schema-invalid input is rejected before charging. These are exactly the operational facts an agent needs before calling a paid tool.

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?

Two dense sentences, front-loaded with purpose then return shape then cost. Slightly packed — type list, output shape, caps, and pricing are compressed into very long clauses — but no sentence is wasted.

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 no output schema present, the description fully specifies the return object and counts, plus the caps, redaction behavior, and billing semantics. Nothing material is left for the agent to guess.

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 100%, so baseline is 3; the description adds genuine meaning by stating the nine fixed types default to all and that returned spans are verbatim substrings, a semantic constraint not expressible in the schema. It does not restate the 8,000-character limit, which the schema already carries.

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+resource ('Named entities ... each found verbatim in your text') and enumerates the exact fixed type set, which alone distinguishes it from generic siblings like keywords, classify, or pii-redact. An agent knows precisely what it gets back without opening the schema.

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 phrase 'fixed types' and the enumerated taxonomy imply scope, but there is no explicit when-to-use or when-not-to-use guidance and no named alternative (e.g. pii-redact, keywords, web-extract). Usage is inferable rather than stated.

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