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

Adds substantial non-obvious behavior beyond the annotations: device 'exclusion' is actually a 0 bid modifier because the API rejects `negative: true` on DEVICE criteria, and Google auto-creates MOBILE/TABLET/DESKTOP criteria so exclusion updates existing criteria while CONNECTED_TV gets created new. It also clarifies the additive nature of location targeting. No contradiction with destructiveHint=false or idempotentHint=false.

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-loads the purpose in the first sentence, then spends space on genuinely non-obvious mechanics. It is long and partially duplicates the excludeDevices schema description, which is a minor redundancy, but every sentence carries information an agent would otherwise lack.

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 7-parameter mutation tool with no output schema and openWorldHint=true, the definition covers defaults, the broadest-reach trap, and the device-criterion mechanism. It does not describe the return payload or confirm what a successful call reports, leaving a modest gap.

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 already 86%, so the baseline is 3; the description goes further by explaining the mechanism behind excludeDevices and clarifying that geoTargetIds is additive to existing criteria. It does not add new meaning for adSchedule or validateOnly 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?

States a specific verb+resource set: 'Add positive location targeting, device exclusions, and/or an ad schedule (day-parting) to a campaign.' It precisely enumerates the three capability areas and is distinguishable from siblings like update_campaign, get_campaign_criteria, and remove_campaign_criterion.

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 clear conditional guidance: 'set this before enabling any campaign meant for specific markets,' and warns that omitting location criteria defaults to Google's broadest reach. It does not name alternative tools (e.g., when to prefer update_campaign) or state exclusions, so it stops short of a 5.

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