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

Annotations already mark destructiveHint=true. The description adds context by stating 'triggers a real send' and 'cannot be undone', reinforcing the irreversible nature. It does not contradict annotations and provides meaningful behavioral insight beyond 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?

Two sentences, front-loaded with the core action, no extraneous words. Every sentence earns its place by stating the action and its irreversible consequence.

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 main action and consequence, but does not mention expected return values, prerequisites (e.g., test state), or error conditions. Given no output schema, slightly more detail on outcome would improve completeness.

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 100%, so the schema already documents all parameters (test_id, winner_variant, metric). The description adds no additional meaning or guidance for any parameter, achieving only the baseline.

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 tool selects a winning variant and sends it to the remaining audience, using a specific verb and resource. It distinguishes from siblings like create_ab_test and list_ab_tests by focusing on the selection and execution step.

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 implies this is the final action in an A/B test (triggering a real send) and warns it cannot be undone, but it does not explicitly state when not to use it or suggest alternative tools for previewing or cancelling.

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