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

Annotations only say readOnly/openWorld, so the description carries the real burden and adds genuinely non-obvious facts: a credit cost, that missing region means a global search (relevant to result volume and relevance), and that postCount/adCountUpper are the published range bounds counted within region. It does not cover result volume, ordering, or paging behaviour, so it is not fully transparent.

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?

Front-loaded with purpose, then the output contract, then the region caveat, then cost — a sensible priority order. Sentences are dense and mostly earn their place, though the telegraphic phrasing of 'Advertisers matching a name, with the advertiser id that ... needs' is harder to parse than it needs to be.

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 no output schema, the description usefully supplies return shape (advertiser id, domains, ad-count bounds) and the credit cost. Combined with annotations that cover the safety profile and a mostly documented schema, an agent has enough to call it correctly; only cache_max_age and result-ordering/paging are unaddressed.

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 67%; query and region are documented in the schema, and the description reinforces region's 'omit to search every region' behaviour. cache_max_age is undocumented in both places, leaving a gap. The remaining sentences explain return fields (domains, postCount, adCountUpper) rather than parameters, so they do not raise this dimension.

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 and resource (find advertisers in Google's Ads Transparency Centre) and immediately clarifies the scope of the result: advertisers matching a name, plus the verified domains Google suggests. Critically it ties itself to a sibling, noting the advertiser id is what /v1/google/ad-library/advertiser-ads needs, so an agent can place it in a workflow without opening a schema.

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?

Gives a clear downstream path: use this tool first to obtain the advertiser id, then feed it to the advertiser-ads tool. Also notes that omitting region widens the search to every region, which is a usage decision. It stops short of naming an alternative for the same task (e.g. facebook_adLibraryAdvertisers or google_advertiserAds) or stating when not to use it, so not a 5.

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