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

With no annotations provided, the description carries the full burden, and it excels: dry_run defaults to true and the two-call pattern is explicit, delete is described as PERMANENT with auto-pausing of ad sets and a preview listing them, and the lookalike_country deprecation (silently ignored) is disclosed. The TOS acceptance requirement adds an operational caveat. This is far beyond the minimum.

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 long, but justified by the tool's complexity (12 params, four audience types, a destructive delete path). It is front-loaded with the core action and types, then dry_run, then critical warnings, then exclusions. Each sentence provides distinct value, though it could be tightened slightly without losing content.

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?

Given no annotations and no output schema, the description covers the essential operational context: required actions, dry_run semantics, destructive consequences, TOS prerequisite, and unsupported case. It does not describe the response/return format for create/update previews, but the lack of an output schema makes this a minor gap rather than a critical omission for a management tool.

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 100%, so the baseline is 3. The main description adds general guidance (e.g., rule vs lookalike fields, dry_run behavior) but the detailed parameter semantics are already in the schema descriptions. It does not meaningfully extend beyond the schema for individual parameters, and the rule-construction details live in the schema, not the tool description.

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-resource pair: create, update, or delete rule-based custom audiences, and enumerates the four supported types (Website, Engagement, Lookalike, App). It clearly differentiates from the sibling adsap_list_custom_audiences by positioning this as the write counterpart and explicitly excludes customer-list uploads, leaving no ambiguity about scope.

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?

The description gives explicit when-to-use guidance: it names the read sibling for lookups, states what is NOT supported (hashed customer lists), and instructs on the dry_run workflow (preview first, then apply). It also flags the Meta TOS prerequisite and the deprecation of lookalike_country, helping the agent decide when and how to invoke the tool correctly.

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