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

Annotations declare destructive/not-idempotent, but the description adds the crucial dry-run contract ('Previews unless confirm is true') and the removal-by-text matching semantics, which the annotations cannot convey. That is exactly the extra behavioral context an agent needs before mutating live campaign data.

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 clauses, front-loaded with the action and scope, then the trigger, then the preview rule. No filler and 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?

For a destructive, non-idempotent mutation with no output schema, the description covers when to use it, its scope limits, and the preview/confirm gate. The gap is per-parameter detail (item limits, account/campaign identifiers), which is minor given the strong operational framing.

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 only 25%, and the description compensates for the keywords array by implying text-based matching rather than IDs. However, it never mentions the 50-item cap or the role of campaign_id/customer_id, leaving half the parameters undocumented in both schema and prose.

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 ('Remove negative keywords from a Google Ads campaign'), specifies the matching key ('by their text'), and bounds the scope ('Campaign-level negatives only'). This clearly distinguishes it from the sibling ads_add_negative_keywords and from list/status tools.

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 trigger condition ('use when a negative blocks searches the client wants') and an explicit boundary ('shared negative lists are not changed'). It stops short of naming the alternative tool to use for shared lists, so it is clear context plus a scope exclusion rather than full routing guidance.

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