Create mediation A/B experiment

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

Annotations indicate destructiveHint=true and readOnlyHint=false, matching the mutation nature. The description adds behavioral context: dryRun behaves as a validation mode, and the default execution requires confirmation. It also discloses the single-experiment-per-group limitation.

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, no fluff. The purpose is front-loaded, and additional details (inheritance, limit, monitoring) are efficiently packed into the second sentence.

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 6 parameters (4 required) and no output schema, the description covers the core purpose, constraints, and dryRun behavior. It references a sibling tool for monitoring. While return value is not described, the agent can infer it from the action. Minor gap in explaining what happens post-experiment.

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?

With 67% schema coverage, the description adds meaning beyond the schema. It clarifies that control lines are inherited (eliminating that param guesswork) and mentions the key params (treatment lines, traffic percentage). The dryRun param gets extra context in the description about confirmation requirement.

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 uses a specific verb ('Start an A/B experiment') and resource ('mediation group'), clearly distinguishing from siblings like admob_stop_ab_experiment. It adds scope details (v1beta, allowlisted) and automatic control line inheritance.

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 explains when to use the tool (to start an experiment) and provides a constraint ('Only one experiment can run per group at a time'). It also suggests monitoring via admob_list_mediation_groups. No explicit exclusion, but context is clear.

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