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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is largely covered. The description adds value by stating the change widens reach and requires confirmation, consistent with the non-destructive write annotation, but it omits whether an account/customer ID context is mandatory, whether radius targeting replaces or appends, and what the call returns.

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?

Two short sentences, no filler; the core action leads and the confirmation caveat follows. The second sentence is telegraphic ('Widens reach, so...') but still earns its place by flagging a required precondition.

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?

For a 9-parameter mutation tool with no output schema and sub-50% schema coverage, the description covers the essence plus one precondition. It is missing the details an agent would want before calling: unit defaults, whether an account parameter is required, and the effect of dry_run/confirm=false.

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 only 44% across 9 parameters, so the description has to carry weight. It reinforces latitude/longitude/radius and the confirmation requirement, but says nothing about `unit` (enum, and what happens if omitted), `account`, `dry_run`, or `label`, leaving several undocumented parameters unaccounted for.

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 concrete verb plus resource ('target people within a radius of a point ... on a campaign') and names the key inputs (latitude/longitude). It is distinguishable from sibling tools like google_ads_add_keywords or google_ads_display_targeting, but it never names an adjacent alternative such as google_ads_find_locations or google_ads_campaign_targeting.

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?

'so it needs confirmation' gives one real usage rule (get explicit user consent before invoking), which is genuinely actionable. However, it gives no guidance on when to prefer this over other targeting tools, what to do if a location must be looked up first, or what happens if the campaign already has radius targeting.

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