Draft attaching a shared set

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

The description transparently discloses non-obvious behavior: it returns a PREVIEW and requires a subsequent call to confirm_and_apply to actually execute. This goes beyond the annotations (readOnlyHint=false, destructiveHint=false) which do not capture the preview/confirm pattern. The agent is fully aware of the tool's side effects.

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 repeats the preview/confirm behavior in the first and last sentences, which is slightly redundant. However, the overall structure is logical: summary, detailed explanation, parameter notes. It is not overly long and the redundancy reinforces the critical workflow.

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 provides all necessary context for an agent to act: what the tool does, how it relates to other tools (get_negative_keyword_lists, confirm_and_apply), the fact that it returns a plan_id, and the need for confirmation. It is self-contained enough to guide the agent without needing additional references.

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 adds meaning for shared_set_id and campaign_ids (including numeric type and how to obtain them), but does not explain customer_id, which is a common but still important parameter. Coverage is good for 2 of 3 params, and the extra guidance on deriving shared_set_id from get_negative_keyword_lists is valuable.

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 identifies the action (attach), the resource (shared set), and the target (campaigns), and distinguishes it from related tools like detach_shared_set_from_campaigns. It also explains the purpose (inheriting negative keywords) precisely.

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 explicitly states the common use case ('Most commonly used to attach a shared negative keyword list to newly-built campaigns') and provides the full workflow: fetch the shared_set_id, attach, then confirm with confirm_and_apply. This gives the agent clear guidance on when and how to use the tool.

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