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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered; the description adds valuable context beyond that: pre-send verification of operation kind, approval integrity and state drift, plus a no-replay idempotency rule for uncertain outcomes.

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 dense sentences, front-loaded with the action and its approval precondition, with zero filler. Each sentence carries distinct information: trigger, input provenance/validation, and failure handling.

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-step mutation with no output schema, it covers the trigger, the input provenance, pre-send validation and the uncertain-outcome path. It stops short of describing what the initiation actually does to the experiment (budget/traffic impact), which is the main remaining gap.

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). The description compensates partially by explaining that draft_id must be the matching draft from the prepare step, but connection_context is left entirely to its regex pattern and no parameter format details are added.

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 (initiate) and resource (an existing experiment in SETUP), plus a precondition, which clearly distinguishes it from the sibling google_ads_experiment_initiate_prepare and from halt/action/promote variants.

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?

Explicitly gates invocation on prior approval and on a matching draft produced by google_ads_experiment_initiate_prepare, and routes uncertain outcomes to reconciliation rather than replay. Both the trigger condition and the alternative path are named.

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