Create a customer-list audience from contacts with confirmed consent (201)

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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds the meaningful facts that the call is gated behind confirm: true and that omitting it returns a request preview rather than executing. It does not cover failure behavior on consent rejection or the 201 response semantics, but it substantially exceeds the annotation coverage.

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 short sentences with the resource and endpoint front-loaded and the write-gate warning immediately after. The parenthetical '201' and repeated title phrasing are slightly redundant but cost little.

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?

For a write tool with a nested object payload and no output schema, the definition covers the safety gate well but leaves the body shape — row limits, email/phone requirements, consent basis — entirely to the schema. An agent knows how to execute safely but not what a valid payload looks like beyond required fields.

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 67%, with confirm and idempotencyKey already documented in the schema; the description reinforces confirm's gating role. The nested body fields (rows, consent.basis, clientId, defaultCountryCode) get no added meaning beyond 'contacts with confirmed consent', leaving the largest part of the payload unexplained.

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 states a specific verb and resource — creating a customer-list audience from contacts with confirmed consent — and pins it to POST /v1/audiences. The phrase 'customer-list audience' implicitly separates it from audiences_createLookalike and audiences_addMembers, though no sibling is named explicitly.

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 gives a strong execution precondition: nothing is sent unless confirm: true, and there is no server-side dry run. However, it never says when to choose this over audiences_addMembers (adding to an existing list) or audiences_createLookalike, so the routing decision is only implied.

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