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

With no annotations, the description carries the full burden. It discloses the return fields (type, size, freshness, staleness), which adds value beyond the schema. However, it does not explicitly state that the operation is read-only, nor does it mention pagination behavior or any permissions. For a simple list tool this is adequate but not rich.

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 sentences with zero waste. The first sentence packs the verb, resource, and return fields; the second gives the intended use case. Content is front-loaded and every sentence earns its place.

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 list tool with 100% schema coverage and no output schema, the description covers the essential return fields and intended use case. It does not mention pagination, but the cursor parameter in the schema hints at it. This is a minor gap for an otherwise complete definition.

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 all four parameters have descriptive schema text, including the required act_ prefix and the type_filter enum. The description adds no parameter-level detail, so the baseline of 3 applies.

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 ('List'), resource ('custom audiences and saved audiences in a Meta ad account'), and the key return fields (audience type, size, freshness, staleness). This clearly differentiates it from sibling tools like adsap_get_custom_audience_ads or adsap_manage_custom_audience.

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?

Provides a clear use case: 'auditing audience strategy — detecting missing retargeting, stale seeds, untapped lookalikes.' This tells an agent when to use the tool, though it does not explicitly name exclusions or alternatives.

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