Pause Keyword (gated mutation)

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

The annotations already indicate destructiveHint=true, so pausing is destructive. The description adds that it is a 'GATED' mutation requiring an environment variable and explicit user intent, which is critical for safe use. It does not contradict any annotations. It could elaborate on idempotency (e.g., pausing an already-paused keyword), but the idempotentHint annotation covers that.

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 brief sentences contain all essential information: the action, the gating requirements, and the user consent directive. No redundant words; the description is front-loaded with the verb and resource. Highly efficient.

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?

Given the tool has 5 parameters, is gated, and has an output schema, the description adequately covers the purpose, gating conditions, and user interaction required. It does not describe the output format or what happens after pausing, but the output schema exists to cover that. For a mutation tool with these constraints, the description is complete enough to guide safe and correct invocation.

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?

The schema covers 60% of parameters with descriptions, including clear ones for 'criterion_id' and 'customer_id'. The description reinforces the use of 'criterion_id' and adds context for 'explicit_user_intent' by stating the requirement. This compensates for the missing schema description on that parameter. The 'response_format' parameter is documented in the schema with an enum and default, so no additional description is needed.

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 states the action ('Pause'), the resource ('a single keyword'), and the identifier ('by criterion_id'). The title includes '(gated mutation)' to emphasize it's a write operation, and siblings like 'google_ads_resume_keyword' and 'google_ads_pause_campaign' are distinctly different. This fully distinguishes the tool.

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?

The description explicitly warns to 'Ask the user first' and lists the gating requirements (GOOGLE_ADS_ALLOW_MUTATIONS=true AND explicit_user_intent=true). This provides clear context for when to use the tool. However, it does not explicitly list when not to use it or mention alternative tools for related actions like resuming a keyword or pausing a campaign, though the name and sibling tools imply these.

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