pause_keywords

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

Annotations state readOnlyHint=false and destructiveHint=false, and the description adds meaningful behavioral context beyond that: the action is reversible because it pauses rather than removes, and keywords that fail the evidence threshold are kept and reported. This helps an agent understand side effects and outcomes without contradicting the annotations.

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?

The description is brief and front-loaded with the core action and condition. Each sentence adds useful information, though the phrase 'Evidence is measured here' is slightly vague and could be more direct without adding length.

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?

The description covers the core behavior and reversibility, and an output schema exists to explain return values. However, it leaves important operational details unaddressed, such as the purpose of dry_run, how evidence thresholds are computed, and how the tool differs from pause_ad_groups or add_negative_keywords. Given the parameter count and schema coverage, this is adequate but not complete.

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 0%, and the description does not explain any of the six parameters. Parameters like dry_run and rationale are particularly important to understand but are left undocumented. The description provides some context for keyword_texts through the word 'keywords', but it fails to compensate for the lack of schema descriptions.

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?

The description clearly identifies the verb (pause), the resource (keywords), and the specific selection criterion (spending without converting). It also distinguishes itself from removal or permanent actions by explicitly stating it never removes keywords, making its purpose distinct from sibling tools that delete or mutate.

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?

It provides clear context for when to use the tool: keywords that are spending but not converting, with evidence measured against a policy threshold. It does not explicitly name alternatives or say when not to use it, but the reversible pausing behavior implies a preferred use case over removal.

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