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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known without the text. The description reinforces this with an explicit 'VORSICHT: Nicht rückgängig machbar!' warning and clarifies that workspace is optional when the account has only one workspace, but adds nothing about confirmation flow, cascading effects, or what identifier space the IDs live in.

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 lines, no filler, and the destructive warning is placed immediately after the verb. Minor deduction for mixing German body text into an otherwise English tool ecosystem and for folding parameter documentation into the same untitled block.

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?

For a destructive, irreversible mutation with zero schema description coverage, an output schema present, and many similar removal tools, the definition does too little: it never says which keyword namespace criterion_id refers to or how this differs from the status-update path. The irreversibility warning is the one substantive addition.

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% across three parameters. The description explains only workspace ('Slug des Kunden-Workspace, optional bei nur einem Workspace'), while the two required parameters, ad_group_id and criterion_id, remain completely undocumented in both schema and description.

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 and resource ('Keyword entfernen'), so an agent knows the operation is a deletion on a keyword criterion. It does not distinguish itself from near-siblings such as ads_remove_negative_keyword or ads_update_keyword_status (which can also set a keyword to REMOVED), leaving real ambiguity in the crowded ads_* removal family.

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 statement of when to use this instead of ads_update_keyword_status (status change to REMOVED), ads_bulk_update_keyword_status, or ads_remove_negative_keyword. No prerequisites, no exclusions — the agent must infer from the tool name alone.

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