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

Annotations already flag destructiveHint=true and non-idempotent behavior. The description adds crucial operational context: mode='replace' removes existing criteria for the dimensions passed and writes new ones in the same request, and confirm=false previews resolved locations and removals before mutation.

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?

The description is front-loaded with purpose and behavior, but it includes a lengthy rationale anecdote about a live campaign failure. That context is useful but not strictly necessary for invocation, so it is slightly verbose rather than maximally concise.

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 complex, destructive 8-parameter tool with an output schema and no schema descriptions, the description is strong: it covers mutation semantics, preview mode, and read-before-write guidance. It could be more complete by clarifying the country parameter and required IDs.

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 does substantial work: it explains locations, negative_locations, languages, mode, and confirm. It leaves country, customer_id, and ad_group_id largely implicit, though the required IDs are self-evident from the schema names.

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: sets geographic and language targeting on an ad group. It distinguishes itself from campaign-level targeting by explaining that Demand Gen rejects location and language at campaign level, so an agent can tell it apart from siblings like set_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?

Explains exactly when to use this tool: for Demand Gen ad groups, because campaign-level location and language targeting is rejected. It also names the read alternative, get_campaign_targeting(ad_group_id=...), for checking current state.

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