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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds meaningful context that it draws from 'one live Meta ad set' (implying a live-adset precondition), but it doesn't say what the preview contains or whether it mutates any draft state.

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 sentence, front-loaded with the action and resource, with zero redundant text. Nothing could be trimmed without losing information.

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?

With readOnly annotations and an output schema present, return-value explanation is not needed. However, the 0% parameter coverage means the undefined ad_account_id and lack of usage guidance leave clear gaps for a tool an agent must call with two required IDs.

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%, so both parameters are undocumented in the schema. The description only implicitly covers adset_id via 'from one live Meta ad set'; ad_account_id is never explained, nor are ID formats or scoping rules, leaving the description to fall short of the low-coverage bar.

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?

States a specific verb ('Preview') and a specific resource ('reusable audience pack') plus its source ('one live Meta ad set'). Clear enough to distinguish from interests_search or interests_get by origin, though it doesn't name the alternatives explicitly.

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 verb 'Preview' implies a read-only look, but there's no explicit when-to-use, no mention of alternatives like interests_get or interests_search, and no hint that the output feeds interests_save_fetched_pack. An agent must infer the workflow from sibling names alone.

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