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

Annotations already declare destructiveHint=false, idempotentHint=true and openWorldHint=true. The description adds real value by explaining why it is applied immediately (it only reduces spend), which justifies skipping a confirmation step. It does not cover the ambiguous case of supplying neither campaign_id nor ad_group_id, or what happens on duplicate keywords.

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 sentences, front-loaded with the action and scope, and the rationale placed second. Nothing is wasted or repeated from the structured fields.

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 5-parameter mutation tool with no output schema, the essential framing (what it does, where it targets, immediate application) is covered. The remaining gaps are the undocumented match-type semantics on the nested keyword objects and the requirement of one target scope — noticeable but not blocking.

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 40%, and the description compensates only partially: the phrase 'to a campaign (or an ad group)' clarifies that campaign_id and ad_group_id are alternative targets. It says nothing about the keywords array structure, the EXACT/PHRASE/BROAD match values, dry_run, or the 500-item cap.

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 ('Add negative keywords') and gives the scope ('to a campaign (or an ad group)'), which is enough to separate it from remove_negative_keywords and the negative-list tools. It stops short of naming a sibling explicitly, so it lands at a strong 4 rather than a 5.

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?

'Runs immediately because it only reduces spend' implies usage is safe without approval, but there is no explicit when-to-use vs alternatives guidance (e.g. campaign-level negative keywords vs a shared negative list, or when to preview with dry_run). Context is implied rather than stated.

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