direct_get_autotargeting

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

With no annotations, the description carries the safety burden; it does state 'READ' which indicates a read-only operation. It also discloses the specific data returned (autotargeting rows, categories, bid). However, it provides no further behavioral context such as filtering, pagination, or output format.

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 telegraphic but contains all key elements: operation (READ), resource, and relevant parameters. It's front-loaded and avoids filler, making it highly 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 simple get tool with two parameters and no output schema, the description provides the return components but leaves ambiguity around parameter usage (e.g., whether campaign_ids are needed when project is set, and what 'all' or 'unknown' mean for project). It lacks context on how the parameters interact.

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?

The description merely echoes the parameter names 'project/campaign_ids' without adding meaning. The schema already documents 'project' in Russian, but 'campaign_ids' remains undocumented. The description does not clarify whether parameters are required, optional, or how they relate.

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 uses the explicit verb 'READ' and specifies the exact resource: autotargeting keyword rows, AutotargetingCategories, and Bid. This clearly distinguishes it from write tools like direct_set_autotargeting, though it doesn't explicitly compare with sibling get 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 offers no guidance on when to use this tool versus alternatives like direct_get_keyword_bids or direct_get_negatives. It only states the operation, leaving selection to the agent based on the resource name.

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