targeting_keywords_find

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

No annotations are provided, so the description carries the full burden. It does not explicitly state the operation is read-only or list side effects. However, it does disclose a key behavioral trait: Apple does not expose a per-ad-group find, which is useful context. This adds value beyond the schema but lacks full transparency on safety or output behavior.

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?

Two concise sentences, each serving a distinct purpose: the first states what the tool does, and the second provides an important behavioral note. No extraneous words, and critical information is front-loaded.

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?

The description is missing information about return values (no output schema) and potential edge cases. It does cover the key contextual point about the lack of per-ad-group find, which is critical for correct usage. Given the tool's complexity (selector with pagination, multiple parameters), the description provides important context but leaves some aspects (e.g., default fields, error handling) unspecified.

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 description coverage is 67% (selector and orgId have descriptions). The description adds marginal parameter guidance by suggesting using the selector's conditions to filter by adGroupId, which helps agents understand the selector's purpose. It does not elaborate on campaignId or orgId beyond what's in the schema. Baseline 3 is appropriate given coverage and limited added detail.

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?

The description clearly states the tool finds targeting keywords across all ad groups in a campaign with a selector, specifying the scope (all ad groups) and mechanism (selector). It also distinguishes from per-ad-group find by noting Apple's lack of such an API, which differentiates it from sibling tools like targeting_keywords_list or adgroup-level find tools.

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 explicitly addresses a common use case: needing per-ad-group filtering. It advises filtering by adGroupId in the selector, providing clear context. However, it does not directly contrast with sibling tools like targeting_keywords_list or specify when to use this tool versus alternatives, leaving some inference to the agent.

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