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

The annotations already declare destructiveHint=true and openWorldHint=true, so the description's "VORSICHT: Nicht rückgängig machbar!" restates the annotation rather than adding new information. It does not say what else is lost (historical performance data, ad review status) or whether confirmation/republishing is possible. It is consistent with the annotations but adds little beyond them.

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?

Two short sentences with the destructive warning front-loaded immediately after the action, which is the right ordering for a delete tool. Nothing is wasted, though the terseness leaves gaps that structure alone cannot compensate for.

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 not be described, and annotations cover the safety profile. Still, for a destructive, open-world mutation with three undocumented parameters, the description omits what identifier format ad_id expects, what happens to dependent entities, and what a successful removal returns — gaps that matter before an irreversible call.

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 0%, so the description carries the burden — it partially meets it by explaining that workspace is a customer slug that is optional when only one workspace exists, which the schema's bare `default: null` does not convey. ad_id and ad_group_id are left entirely unexplained, and the required nesting/ad-group relationship is never stated.

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?

"Anzeige entfernen" states a specific verb and resource, so the agent immediately knows this deletes an ad. It does not distinguish itself from close siblings such as ads_remove_ad_group, ads_replace_ad, or ads_update_ad_status (pause-vs-delete), which is the one thing missing. The German wording against an English tool name adds minor friction but the meaning 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?

There is no guidance on when to delete an ad rather than pause it via ads_update_ad_status, replace it via ads_replace_ad, or remove the whole ad group. No preconditions (e.g. ad must exist, minimum ad count per group) are stated. The agent must infer usage entirely from the tool name.

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