pause_ad_groups

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

With annotations already establishing readOnlyHint=false and destructiveHint=false, the description adds value beyond them through 'Pauses, never removes,' a firm reversibility/non-removal commitment, plus the threshold logic governing the decision. It does not contradict any annotation; pausing is consistent with a mutating yet non-destructive operation.

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 sentences deliver the action, the safety boundary, and the threshold rationale with zero filler. The core purpose is front-loaded and every clause earns its place.

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?

An output schema covers return values and the core behavior and decision logic are well explained. However, for a mutating tool the most useful guardrail, dry_run, is never mentioned, and the connection between run_id and the revert_last_run sibling is left implicit — adequate overall, but with clear gaps around parameter behavior.

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%, so the description must compensate for undocumented parameters, but it only partially does. 'Whole ad groups' clarifies that ad_group_names expects full group names and 'spending without converting' hints at the rationale field, yet run_id, dry_run, customer_id, and campaign_id are left entirely unexplained.

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 opens with a specific verb-resource pair — 'Pause whole ad groups that are spending without converting' — and adds the behavioral boundary 'Pauses, never removes.' The threshold remark referencing keywords differentiates it from the sibling pause_keywords tool without needing to open either schema.

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 states the triggering condition ('spending without converting') and explains why thresholds are calibrated differently ('an ad group is a much bigger unit to switch off'), giving clear context for when to invoke it. The keyword-level counterpart is strongly implied by the threshold comparison, but the alternative is not explicitly named and no when-not-to-use exclusions are stated.

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