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

No annotations are provided, so the description carries the full burden. It does add real behavioral value — the audience starts empty and ready, costs no credits, and is filled via a separate call — but it omits whether the name must be unique, what identifier comes back (which the follow-up call presumably needs), and any permission prerequisites.

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?

A single front-loaded sentence with two trailing clauses, each of which earns its place (next step, alternative path, cost). No repetition of the title or name.

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 one-parameter creation tool with no output schema, the description covers purpose, prerequisites, cost, and the follow-up call. The main gap is the return value (audience id), which the chaining instruction implies exists but never names.

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 0% for the single required `name` parameter, so the description is the only source of semantics. It conveys that the audience is 'named' but adds no constraints or rules beyond the schema's own minLength/maxLength, which an agent could read directly.

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?

A specific verb plus resource ('Create an empty, named custom audience'), with initial state disclosed ('status ready'). It also names the two siblings it is not — add_custom_audience_contacts and upload_custom_audience — so the agent can separate it from them without reading schemas.

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?

Explicit routing: use this first then fill it with add_custom_audience_contacts; use upload_custom_audience when the source is a file. The condition that selects the alternative is stated outright, leaving nothing to inference.

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