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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description contributes additional behavioral facts: this is a name-required lookup, supports partial match, pagination, sorting, and is not an account-wide browse. It does not describe edge-case behavior such as no matches, but with annotations covering the safety profile this is solid.

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 description is compact and front-loaded: it states the core capability, then the required-name caveat, and then the use cases. The first sentence and the USE FOR paragraph are slightly redundant with each other, but no sentence is wasted.

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 read-only tool with a clear schema and annotations, the description communicates the return categories (configuration, targeting, size, performance) and the lookup mechanism. It never mentions what an empty result or not-found response looks like, but the explicit name precondition and use cases are enough for most agents to call it correctly.

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%, and the schema already documents the name's partial matching, page, size, and detailed sort rules, so the description carries no extra burden by default. The description's 'paged, sortable' and 'A NAME IS REQUIRED' largely restate schema semantics rather than adding new meaning.

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 names a specific operation—by-name lookup of custom audience details—and enumerates the returned content areas: configurations, targeting criteria, size metrics, and performance. It also distinguishes itself at a high level from an account-wide browse, though it does not explicitly name sibling tools like list_audiences or get_deep_audience_details.

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 explicit use cases ('USE FOR: resolve an audience the user named, read its configuration/targeting, review size/performance') and a key precondition: a name is required. The 'not the account-wide browse' clause gives a when-not, but it does not point to a specific alternative tool, so it stops short of full routing guidance.

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