Draft demographic targeting

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

The description is transparent about the tool's non-committal nature: it 'returns a PREVIEW' and requires a separate confirm_and_apply call to execute. This aligns with the annotations (readOnlyHint=false, destructiveHint=false) and clarifies that no immediate changes are applied.

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 well-organized with clear sections and bullet lists, making the constraints and accepted values easy to scan. It avoids fluff and each sentence serves a purpose, such as explaining the default negative behavior and the requirement to call confirm_and_apply.

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?

Given the tool's complexity (multiple optional lists, negative flag, and confirmation step), the description provides sufficient context: it states the preview nature, the required selection constraints, the exact accepted enum-like values, and the follow-up action. This is enough for an agent to use the tool correctly without additional documentation.

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 thoroughly explains the meaning and accepted values for most parameters, including negative boolean, age_ranges, genders, parental_statuses, and income_ranges with country limitations. However, customer_id is present in the schema but not mentioned in the description, leaving its role or necessity unaddressed.

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's action ('Draft demographic targeting') and the specific resource it operates on (age/gender/parental status/income segments). It also distinguishes its preview-only behavior and explicitly points to confirm_and_apply for execution, which differentiates it from related 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 explains when to use the tool (to exclude or narrow demographic targeting) and provides key constraints: exactly one of ad_group_id or campaign_id, and at least one demographic list. It also lists all accepted values and instructs to call confirm_and_apply with the returned plan_id, giving clear next-step guidance.

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