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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known; the description adds real value on top by warning that removals 'can increase traffic and spend' and by promising the response echoes exactly what was removed so it can be re-added. It does not spell out behavior for text matches that hit more than one negative, a small remaining gap.

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?

Four sentences, each doing distinct work: effect, scoping/matching, consequence, and reversibility. The scope rule and the dryRun advice are front-loaded where an agent will hit them first.

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?

There is no output schema, and the description compensates by stating that the response returns exactly what was removed. Combined with spend-warning, dryRun guidance, and undo path, an agent has everything needed to call this destructive tool safely.

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 100%, so the schema already documents dryRun, matchType, accountId, and the rest; baseline 3 applies. The description restates matchType and adGroupId semantics but adds no syntax or format detail beyond what the schema provides.

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') plus the scope variant: campaign-level by default, ad-group-level when adGroupId is given. That also cleanly distinguishes it from its sibling msads_add_negative_keywords, which is named later as the inverse.

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 concrete routing conditions: use adGroupId to target an ad group's own negatives, add matchType to narrow to one match type, and 'Use dryRun first when unsure' with an explicit prerequisite. It also names the recovery path (msads_add_negative_keywords), so the agent knows both when to invoke and how to undo.

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