add_negative_keyword

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds context the annotations cannot: exact match is the default, the concrete effect on ad delivery, and that the change is reversible via Apple Ads › Change history. It also flags the preview/approval gate, which is meaningful operational context for a write 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?

Front-loads the most important signal ('PREVIEW ONLY') and keeps four short sentences, each carrying distinct information. Slightly denser than necessary — the precedence statement and the delivery effect could be tightened — but nothing is filler.

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 effect, reversibility, scope selection, and the approval requirement, which is enough to invoke it correctly. It does not describe what the call returns or how the preview state is later confirmed, minor omissions against a rich annotation set.

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 only 25% (just adGroupId), so the description has to compensate, and it does for the two least obvious inputs: it explains that adGroupId selects ad-group scope versus campaign scope, and that matchType defaults to EXACT. 'text' and 'campaignId' are left to intuition, which is a minor gap.

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+resource ('add a negative keyword') with precise scope: an Apple Ads campaign, or one ad group when adGroupId is supplied. The 'PREVIEW ONLY' prefix and the delivery effect ('searches matching it stop showing the ad') separate it from positive-keyword siblings like add_keywords and add_exact_keyword.

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 the condition that switches scope ('or to one ad group when adGroupId is given') and a hard usage gate ('apply only with the user's explicit approval'). No sibling tool is named as an alternative, so it stops short of full when/when-not routing.

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