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

Annotations already declare readOnlyHint/idempotent/non-destructive, so the description's 'READ-only' is partly redundant, but it adds real behavioral context: the Demand Gen limitation where campaign-level reads return only device criteria, and that location values come back as geo IDs needing lookup. It stops short of describing pagination or throttling.

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 and mostly efficient, but the parenthetical about 'measured on a live campaign that had 27 ad-group locations the campaign read could not see' is anecdotal padding that does not help the agent call the tool. The core operational facts would survive trimming.

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 read tool with an output schema (so return shape needn't be documented) the description covers what is read, both scoping modes, and the Demand Gen edge case. Only customer_id semantics and any pagination/limits 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?

With 0% schema description coverage the description must compensate, and it does for the two optional IDs: campaign_id empty means all campaigns and ad_group_id switches the read to ad group level. customer_id is not clarified, and the geo-ID output format is covered but not parameter typing, leaving a small 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+resource: reads a campaign's current targeting, and enumerates the exact criteria returned (geo/radius/language/device/audience plus negatives) and the geo_target_type semantics. It also distinguishes the ad_group_id mode from the campaign-level mode, so an agent can separate it from siblings like set_campaign_targeting or manage_audience_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?

Explicitly says when campaign_id is empty (all campaigns), when to use ad_group_id (ad group criteria; the only way on Demand Gen), and routes geo-ID resolution to geo_target_search. The when/when-not conditions are spelled out rather than implied.

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