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

Annotations already flag destructiveHint=true and non-readOnly, so safety is covered structurally. The description adds real context beyond them: it verifies operation kind, approval integrity and state drift before sending, and warns that uncertain outcomes must be reconciled without replay. That non-idempotent/no-retry disclosure is exactly the kind of behavior an agent needs and can't get from 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?

Three tight sentences, front-loaded with the action and resource, then prerequisite, then integrity/reconcile behavior. No filler.

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 destructive confirm tool with no output schema and 3 params, it covers the essential call path (prepare prerequisite), the pre-send verification, and the failure-handling rule. The main omission is any indication of the result on success and the unexplained connection_context parameter.

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 only 33% (only customer_id is documented), so the description carries more burden. It mentions customer_id and draft_id but adds no format or semantics for draft_id, and says nothing about connection_context or its mctx_v1 pattern. Partial compensation for a real gap.

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 (confirm promote), the resource (a Search experiment), and the mechanism (copying trial settings to the control campaign). It explicitly names the prepare sibling it depends on, so an agent can distinguish it from google_ads_experiment_promote_prepare without opening a 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 clearly states the prerequisite: 'Accepts only a matching draft from google_ads_experiment_promote_prepare', which routes the agent to prepare first. It also gives a fallback rule for uncertain outcomes. It stops short of naming the reconcile tool explicitly or spelling out when-not to call.

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