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

Beyond the readOnly/idempotent annotations, it discloses cost and auth ('free and needs no account'), the no-guessing fallback ('unrecognised, never guessed'), the PECR default that excludes sole traders and ordinary partnerships on email audiences, and the lawful basis. These are exactly the behavioural traits an agent cannot infer from structured fields.

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?

Purpose and the readback instruction are front-loaded, and no sentence is filler. The closing compliance and PECR sentences are dense but each carries distinct information; the paragraph could be split for scannability but nothing is redundant.

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?

Cost, compliance defaults, fallback behaviour and the next step are all covered, and the output schema means the returned chips/readback need not be detailed. Minor gap: it references a toggle that changes subscriber inclusion, but no such parameter appears in the input schema, leaving the agent unsure how that switch is set.

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%, with the brief example and dataset liveness already documented in the schema, so the description is not required to carry parameter detail. It adds only indirect context about how unmatched words are handled and about the email/corporate-subscriber default, which touches dataset behaviour but does not explain the enum itself. 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?

The description gives a concrete verb and resource — compiling a plain English brief into an audience definition — and enumerates the returned artifacts (readback sentence, editable chips, clarifying questions). Its role is clearly separated from the counting step by naming count_audience as the follow-on.

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?

It states explicitly when to use it first ('for a request in words'), what to do with the result ('read the readback to the user and settle the questions before counting'), and which tool to call next. That is a full when/when-not/next-step routing instruction.

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