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

Goes well beyond the destructiveHint annotation: it discloses that add-mode takes the union rather than narrowing reach, that replace removes and replaces only the dimensions you pass, that replacement happens in a single request so the campaign is never left untargeted, that other dimensions are untouched, that an untargeted campaign targets the whole world, and that confirm=false yields a preview. This is exactly the behavioral context an agent needs for a mutating tool.

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 core purpose, then organizes the rest around named parameters with concrete examples rather than boilerplate. It is long but dense and every clause adds operative detail; the only mild cost is length for a single-purpose tool.

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 an 8-parameter destructive write with an output schema present (so return values need no explanation), the description covers the risky semantics thoroughly. The remaining hole is the undocumented country parameter and the required IDs, which the schema names but never explains.

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 0%, so the description carries the full burden, and it does document locations (with formats/examples), negative_locations, languages, mode semantics, and confirm behavior. It omits the country parameter's role and only implicitly covers customer_id/campaign_id, so a small gap remains.

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 (Sets) plus resource (geographic and language targeting on a campaign), and the surrounding prose makes clear it is distinct from read siblings like get_campaign_targeting and from set_ad_group_targeting. An agent can identify the operation immediately.

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 explains mode='add' vs mode='replace' semantics and gives a concrete selection case ('Use replace to go from all of Türkiye to only Ankara'), which is the key decision for this tool. It does not explicitly compare against sibling tools, but for the core mode decision the guidance is clear.

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