negative_keyword_delete_preview

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

Annotations already declare readOnlyHint=true and destructiveHint=true, and the description usefully sharpens that with 'irreversible', telling the agent there is no undo. It also adds the 'paused campaign' scoping constraint. It stops short of explaining that the preview performs no mutation on its own and must be followed by an apply call, but the annotation baseline is well complemented.

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 front-loaded sentence with no filler. The destructive core of the tool is stated first and the scoping constraint trails it.

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 covers return values and annotations cover safety, but two gaps remain: the description never links this preview to the apply step that actually deletes, and the 'under a paused campaign' clause is ambiguous (is a paused campaign a requirement, and what happens if the campaign is active?). For a destructive-path preview tool, that ambiguity could cause a wrong selection.

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 is 75%, with profile, adAccountId and expectedText already documented in the schema; only 'id' is bare. The description adds nothing about parameter behavior — notably it never explains that expectedText acts as an optimistic-concurrency guard against deleting the wrong keyword. Baseline 3 is appropriate when the schema does most of the work.

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 (preview deletion), a specific resource (negative keyword), and a cardinality scope ('one', distinguishing it from negative_keywords_bulk_* siblings). An agent can tell it apart from negative_keyword_get and negative_keyword_update_preview without opening any 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?

The word 'Preview' implies this is a pre-flight step, and 'under a paused campaign' hints at a precondition, but neither the when-to-use rule nor the follow-up step (operations_apply) is stated. No alternative or exclusion is named, so the agent must infer the preview-then-apply workflow.

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