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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description does add one genuinely useful behavioral note — "No PII dump" — which tells the agent it is safe to surface results, but says nothing about cost, latency, or what happens if the audience cannot be resolved.

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 no padding, and the return-shape information is front-loaded. The "APP:" tag is unexplained noise, and the first sentence is a list rather than a statement of intent.

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 explaining return fields is largely redundant, yet that is the entire description. Meanwhile the two ambiguous, undocumented ID parameters — the real source of ambiguity for this tool — are left completely unaddressed.

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% and both parameters (id, audienceId) are undocumented strings with no explanation of which identifies the audience, whether they are alternatives or mutually exclusive, or what happens when neither optional param is supplied. The description does not compensate at all for this gap.

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 reads as a return-value summary ("Returns audience count, excluded/suppressed count, source, and warnings") rather than a statement of action on a resource. Combined with the name preview_audience an agent can infer it previews an audience's size, but the verb is only implied and the confusing "APP:" prefix adds no purpose information.

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?

There is no guidance on when to call this versus the obvious sibling build_audience, nor on prerequisites (does an audience need to exist first, or can it be previewed inline?). The only hint is the implicit 'preview before build' workflow, which the agent must infer.

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