Ads rollback

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety bar is partly covered. The description adds genuinely new behavioral context: the operation is scoped to a tenant's signed audit trail, it restores previously updated fields, and it deletes objects that the original change created — exactly the kind of consequence detail annotations cannot convey.

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 sentence that front-loads the verb and the data source, with the selection rule parenthesized for compactness. It is dense but every clause carries information; the only cost is that the compressed phrasing around 'latest reversible change of this tenant' reads slightly awkwardly.

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, but this is a destructive, non-idempotent mutation and the description says nothing about the confirm parameter, what happens when no reversible change exists, or whether the rollback itself is recorded in the audit trail. Those are meaningful gaps for an operation of this risk level.

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 0%, so the description must carry both parameters. It clarifies audit_index as the selector for a specific audit-trail entry, which is real added meaning, but the 'confirm' parameter is never mentioned at all — its type, required value, or purpose remain entirely opaque to the agent.

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 gives a specific verb+resource: undo a Google Ads change sourced from the signed audit trail, restoring updated fields and removing created objects. That is far more informative than the bare name, though it never distinguishes this from the related google.api.rollback or ads.change_history siblings an agent might mistakenly pick.

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 parenthetical '(latest reversible change of this tenant, or audit_index)' implies the default behavior versus the explicit-target behavior, which is useful selection guidance for a caller. However, there is no statement of when to use this instead of ads.change_history (to inspect) or google.api.rollback (for other APIs), and no prerequisite or exclusion is given.

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