keyword_delete_preview

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

Annotations already flag destructiveHint=true, readOnlyHint=true, and idempotentHint=true, so the dry-run, non-mutating nature is partly covered by structured data. The description adds genuine value by calling the underlying deletion 'irreversible', which stresses consequence beyond the generic hint, but it says nothing about what the preview returns, whether approval is needed, or that expectedText guards against stale state.

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?

A single 11-word sentence with the operation, its risk level, and its scope all front-loaded. Nothing to trim.

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?

An output schema exists, so return values need no explanation, and annotations carry the safety profile. The only gap is the unexplained relationship to the paused-campaign precondition and the follow-up apply step; given how lean the tool is, that is a minor omission.

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 coverage of 75% is high, so the baseline of 3 applies, and profile, adAccountId, and expectedText are already documented in the schema. The description does not explain the optimistic-concurrency role of expectedText or the undocumented id parameter, so it adds little beyond the schemas.

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 verb-plus-resource combination ('Preview irreversible deletion of one keyword') is specific and clearly separable from siblings like keyword_pause_preview, keyword_update_preview, or negative_keyword_delete_preview. The scoping phrase 'under a paused campaign' narrows intent further, though it reads ambiguously, since there is no campaign parameter to enforce it.

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?

Nothing says when to choose this over alternatives or what to do next; there is no mention that it is a preview step that presumably feeds operations_apply, and no statement of conditions or exclusions. The agent must infer the whole workflow from the name.

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