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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so 'Read-only, no credit' largely restates structured data. The description does add real behavioral context beyond annotations: that Google's suggestion list is fuzzy and may include similarly-sounding provinces/cities, and that the tool returns the full candidate list with level and parent so an exact id can be chosen.

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?

Three short paragraphs, front-loaded with what the tool returns and then the when-to-use rationale. It is slightly longer than strictly necessary, and the enum list for `level` partially duplicates the schema's value list, but every sentence contributes.

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?

An output schema exists, so return-value explanation is not required, and the description still usefully previews the shape of results (id, level, parent). For a read-only lookup with one required parameter, the only meaningful omission is the behavior of `limit` and how many candidates are returned by default.

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% and none of the four parameters carry descriptions, so the description must compensate. It does for two: `country` is described as a 2-letter code narrowing candidates, and `level` is explained as a loose-match filter with its accepted values enumerated. `limit` is left undocumented, so it does not fully close the gap.

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 ('Finds Google's location targeting IDs by name') and names exactly what comes back — id, administrative level, canonical name. It is clearly distinguishable from sibling geo tools like microsoft_location_search or chatgpt_ads_geo_lookup because it is scoped to Google Ads target IDs.

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?

Explicitly tells the agent when to use it: before set_campaign_targeting, specifically when the place is smaller than a city, and explains why (ambiguous bare district names, fuzzy suggestion lists). The alternative — passing a name directly — is implicitly ruled out with a stated reason.

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