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

Annotations already flag destructive=true and openWorld=true, so the bar is lower, but the description still adds what the annotations cannot: irreversibility, that removal is implemented as a status change to REMOVED, and the exact two-step preview-then-confirm flow. It also pins confirm_name to the previewed name, closing the main footgun of a destructive tool.

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?

Three short sentences, front-loaded with the destructive effect and irreversibility, then the required procedure, then the safer alternative. No filler and nothing buried mid-sentence.

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?

Covers the safety-critical behaviour for a destructive tool with no output schema, and the return value need not be described. It could say a bit more about scope — whether removing a campaign cascades to its ad groups/ads and keywords, or which account is used when 'account' is omitted — but nothing essential to invoking it safely is missing.

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 80%, so the schema already documents id, account, confirm, and confirm_name individually. The description adds genuinely new meaning by explaining that confirm and confirm_name are only set on the second call and that confirm_name must match the preview exactly, though it leaves the 'call once to get the preview' trigger implicit (presumably confirm omitted/false) and says nothing about the account parameter.

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 plus the four resources it acts on and names the resulting state (status REMOVED), which is far more than a restatement of the name. The one ambiguity is that 'keywords' could be read as negative keywords, which have their own siblings (google_ads_remove_negative_keywords, google_ads_remove_assets) and are not explicitly excluded.

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?

Gives an explicit decision rule ('Prefer pausing when unsure') that routes the agent to google_ads_pause_campaign instead, and specifies the mandatory two-call confirmation protocol before any removal happens. When-to-use, when-to-avoid, and the alternative are all stated.

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