start_experiment

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

Annotations already flag destructiveHint=true, idempotentHint=false and openWorldHint=true, so the description is not obligated to restate safety. However, it adds nothing beyond them: no mention that this transitions state and is not repeatable, that it begins serving traffic to real users, or what happens to a running experiment.

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?

A single short, front-loaded sentence with no filler. It is efficiently written but arguably too terse for a destructive lifecycle transition.

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 non-idempotent, destructive state transition with no output schema, the description leaves out preconditions, resulting state, and side effects on live traffic. An agent could call it correctly in the mechanical sense but cannot predict the consequences.

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% for the single experimentId parameter, so the schema carries the documentation burden and baseline 3 applies. The description adds no meaning about accepted ID formats or where to obtain the ID.

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 gives a specific verb ('Start') and resource ('A/B test experiment'), so an agent immediately knows the operation. It does not distinguish itself from the closely related siblings stop_experiment and create_experiment, which is the only thing keeping it from a 5.

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?

There is no guidance on when to call this rather than create_experiment or stop_experiment, and no stated precondition such as the experiment needing to exist in a draft or stopped state. The agent must infer the lifecycle from the sibling names alone.

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