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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds material context: the call is free, it requires the audiences:read scope, ordering is newest-first, and PECR defaults exclude sole traders and ordinary partnerships unless a toggle is changed. The lawful-basis note is domain dressing but it explains a real behavioural constraint rather than restating annotations.

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 purpose, the id hand-off, the cost/auth facts and the caveat are front-loaded in a tight sequence of short clauses. The trailing lawful-basis/PECR sentence is the longest and least operational part, costing a bit of density but still earning its place as a caveat.

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?

An output schema exists, so return values need no explanation, and the schema carries all three parameters. Between the two, the description covers selection guidance, cost, required scope, ordering and the domain caveat — nothing an agent needs to call it correctly is missing.

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 q, limit and cursor are fully documented in the schema and the baseline is 3. The description reinforces the name filter and the sort order but says nothing extra about cursor pagination or how limit interacts with the default, so it adds little beyond the schema.

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 opening sentence names a specific verb and resource ('Lists the organisation's saved audiences') and pins down the returned fields (current counts, last refresh), ordering (newest first) and the optional filter. That is enough for an agent to distinguish it from count_audience or get_saved_selections without opening any 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 description states the positive use case ('find an aud_ id to count, quote or share') and explicitly routes the fresh-count case to count_audience. It adds a clear exclusion rule by naming the audience type (email audiences, corporate subscribers only by default), so the agent knows when results will not match naive expectations.

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