Draft an ad group

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

The description explicitly states 'returns a PREVIEW, does NOT create' and mentions atomic keyword inclusion, making the tool's non-destructive behavior clear despite annotations indicating otherwise.

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 concise but slightly redundant (first sentence and second sentence overlap). It is well-structured with clear parameter descriptions and a next-step note.

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?

It provides enough context for a draft operation, including the follow-up action. It does not mention error cases, but for a preview tool it is sufficiently complete.

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 explains the purpose of most parameters: campaign_id, ad_group_name, keywords, and cpc_bid_micros. Only customer_id is left unexplained, but it has a default and is less critical.

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 purpose: 'Draft a new ad group within an existing campaign' and emphasizes it returns a preview, not a creation. This is specific and distinguishes it from creation 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?

It gives usage context by explaining the draft nature and directs the agent to call confirm_and_apply with the returned plan_id. However, it does not explicitly compare with alternatives like update_ad_group, but the preview aspect implies when to use it.

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