ad_delete_preview

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

Annotations already declare readOnlyHint=true paired with destructiveHint=true and idempotentHint=true, so the safety profile is largely pre-disclosed. The description reinforces this with 'irreversible deletion' and adds the paused-campaign constraint, but never explains that the preview itself performs no mutation or that it must be followed by an apply step, leaving the readOnly/destructive pairing to be inferred.

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 the destructive scope and precondition stated first. No filler, nothing redundant, nothing buried.

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 the schema covers most parameters. However, for a high-stakes deletion preview with four required parameters and an expectedText confirmation argument, the description never mentions the confirmation requirement or the preview-to-apply lifecycle, which an agent needs to call it correctly.

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's 'one ad' maps directly to the id parameter, and the schema already documents 75% of parameters including profile and adAccountId. It does not explain expectedText as an exact-match confirmation guardrail, which is the most important semantic behavior of this schema, so a small gap remains.

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 states a specific verb (preview deletion) and a precise resource scope ('one ad'), which lets an agent distinguish it from the many sibling delete-preview tools (ad_group_delete_preview, campaign_delete_preview, keyword_delete_preview, creative_delete_preview). It stops short of naming those siblings explicitly, but the singular-ad scope is unambiguous.

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 supplies one real precondition ('under a paused campaign'), which implies the when-to-use context, but gives no guidance on what to do after the preview, how it relates to the corresponding apply step (operations_apply / ad_delete execution), or when a caller should skip the preview. Usage is implied rather than stated.

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