Draft removing brands from a list

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

Goes well beyond the destructiveHint=true annotation: it discloses that the call is only a preview with a plan_id, that nothing changes until confirm_and_apply runs, and that removal does not detach the list from any campaign. It also explains the underlying reason (no status field), which is real behavioral context the agent cannot get from annotations.

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?

Front-loaded with the most important fact (returns a PREVIEW) and organized into short, digestible paragraphs. There is minor repetition between 'returns a PREVIEW' and 'Returns a preview with a plan_id', and the trailing API doc link adds little value, but overall it is efficient.

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 destructive draft-preview mutation tool, it covers what the call does, the two-step apply workflow, the irreversibility, and the non-side-effect on campaigns. With an output schema present, return values need not be detailed, so nothing essential is missing.

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?

Schema description coverage is 100%, so shared_set_id and criterion_ids are already fully documented (including source tools and irreversibility warnings). The description adds no parameter-specific meaning beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource (remove brands from a brand list) and immediately flags the key output characteristic (returns a PREVIEW). This clearly distinguishes it from add_to_brand_list and propose_brand_list without the agent needing to open a schema.

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?

Explains the essential context for using it: SharedCriteria have no status field, so removal is the only way to take a brand out of a list (nothing to pause). It also names confirm_and_apply as the follow-up step. It stops short of explicitly contrasting with sibling tools like detach_brand_list_from_campaigns, so it is clear context rather than full when-not guidance.

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