Draft ad group changes

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

The description uses the word 'Draft' suggesting a non-destructive, staging operation, but it does not disclose key behavioral aspects such as whether changes are applied immediately, whether a separate confirmation step is required, or what side effects occur. The annotations (readOnlyHint=false, destructiveHint=false) are ambiguous, and the description does not clarify the actual impact of calling this tool. Given the tool name includes 'update', the lack of explicit 'does not apply immediately' is a significant gap.

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 a single, clear sentence with no unnecessary words. It directly states the tool's purpose. The structure is efficient and easily parsed.

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 output schema is not provided, and the description gives no information about what the tool returns (e.g., a draft object, a confirmation message, or an error). Given that this is a drafting tool, an agent would need to know the return format to proceed correctly. The absence of any output details leaves a significant gap in understanding the full workflow.

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 input schema lists four parameters (max_cpc, ad_group_id, customer_id, ad_group_name) with types and defaults but provides no descriptions. The description mentions 'name' and 'manual CPC bid', but it does not explicitly map these to 'ad_group_name' and 'max_cpc'. There is no explanation of what 'customer_id' is for, nor any guidance on required versus optional parameters beyond the schema's required field. This is insufficient for an agent to correctly populate the parameters.

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 'Draft an ad group update for name and/or manual CPC bid', which is a specific verb and object. It distinguishes from sibling tools like 'draft_ad_group' (likely creating a new ad group) and 'update_campaign' (updating a campaign). The only minor ambiguity is the tool name 'update_ad_group' which could imply a direct update, but the description's use of 'Draft' clarifies the intended purpose.

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?

No guidance is provided about when to use this tool versus alternatives. It does not mention that this is for drafting changes to an existing ad group before applying, nor does it reference the broader draft-apply workflow (e.g., 'confirm_and_apply' sibling). Without explicit usage context, an agent may confuse it with a direct update or with creating a new ad group draft.

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