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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context on top: daily refresh cadence, the five-country coverage, the verification method for ai_presenter_only (advertiser-stated or hand-checked), zero cost, tier-based result gating (Pro sees everything, Free sees a short preview), and the card-panel rendering in Claude/ChatGPT.

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 core resource definition and the example intents are front-loaded, and most sentences carry real information. The client-specific rendering note and the 'Costs nothing' line are secondary and could be trimmed or moved after the filtering semantics.

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 five optional parameters and no output schema, the description does the necessary work of saying what comes back (ads shown as cards, truncated for Free users) and what the flags filter on. Minor gaps remain on pagination/limit behavior and on what fields each ad record exposes.

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 60%, so the schema documents limit, country and keyword but leaves product_type and ai_presenter_only bare. The description compensates well for ai_presenter_only by explaining what the flag actually filters on, but never mentions product_type, and adds no format or matching details for keyword beyond the schema.

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 definition names the exact resource: Facebook/Instagram video ads where a person talks to camera, pulled from the Ad Library's UGC tab, with a stated country set and daily refresh. That is specific enough to distinguish it from a generic ad search, but the verb is implicit (it never says 'find/list') and the sibling search_meta_ads is never named, so the boundary relies on inference.

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?

Three concrete example intents ('show me ads done with UGC creators', 'UGC ads with AI presenters', 'UGC ads for digital products') make the intended use unambiguous, and the country/tier scope is stated up front. It gives no explicit exclusions or pointer to alternative tools when the user wants non-UGC or non-video ads.

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