Add targeting

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

The description adds significant behavioral context beyond annotations: replace=true removes existing criteria of the same types first, operator_type EQ includes by default while NE excludes, and only requested targeting should be set. It also documents accepted types and value formats. This is strong transparency for a mutating tool, though auth and error behavior are not covered.

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 compact and front-loaded, moving from purpose to criteria structure to constraints to safety. The type list and examples are useful rather than filler. It is a single dense paragraph, so a more structured breakdown would be slightly clearer.

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 moderate-complexity mutation, the description covers the operation, criteria vocabulary, replacement behavior, and a key safety instruction. The absence of output details is acceptable because no output schema exists and the invocation path is otherwise clear. A note that line_item_id refers to the ad group would close the last remaining 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?

With schema coverage at only 25%, the description compensates well for criteria: it defines the object shape, enumerates targeting types, gives GENDER/AGE examples, and explains operator and replace semantics. account_id is already documented in the schema, but line_item_id remains unexplained beyond its name. Overall parameter meanings are substantially enriched but not fully complete.

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?

Description opens with 'Add targeting on an ad group', providing a specific verb and resource. The detailed criteria list further situates it as a targeting mutation, clearly distinct from list/search tools. It does not explicitly disambiguate from update_ad_group, so purpose is clear but not maximally differentiated.

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?

The description implies this tool is used when the user wants targeting criteria set on an ad group, and it gives operational rules like replace=true and 'Only set targeting the user asked for.' However, it never names alternative tools or says when not to use this one. Usage guidance is present but only implicit.

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