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

With annotations already covering the read-only/idempotent profile, the description adds substantial non-obvious behavior: exact/phrase mirror ADM optimizer matching, broad requires every negative word as a whole word, close variants are not detected, and results are paginated via cursor. These are traits the annotations cannot express.

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 core outcome, then matching semantics, then hypothetical-mode rules. Dense and mostly every sentence earns its place, though the matching-type clause is compressed enough to require a second read.

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?

No output schema exists, and the description does cover what results represent (keyword plus blocking negative with level/id/text) and pagination. It does not specify the returned field names or ordering, a minor gap for a tool with no output schema.

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 100%, so the baseline is 3, but the description adds real inference the schema does not: a hypothetical keyword needs a campaign_id (falling back to the tool's campaign_id), ad-group negatives only apply when an ad_group_id is present, and campaign_id restricts checks to one campaign while account negatives persist. The nested-object shape is only sketched, keeping it below 5.

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 precise verb+resource: lists positive keywords blocked by negatives, and identifies which negative blocks them with level/id/text. Clearly distinguishable from get_negative_keywords and get_keywords in the sibling list.

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 conditions for the 'hypothetical' mode (pass negatives and/or keywords to check words not yet added) and the scope effect of campaign_id, including that account negatives still apply. It does not name a sibling tool to use instead when the user only wants existing negatives (get_negative_keywords), so it stops short of explicit alternatives.

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