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

Adds meaningful behavior beyond the (readOnlyHint=false, destructiveHint=false) annotations: it discloses that it creates a new run (returns a new processId), that it spawns no new variants, and that results must be polled via get_optimization_details. This async/polling contract is exactly the context annotations don't convey; it stops short of describing cost magnitude relative to the scenarioCount tradeoff.

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 tightly-scoped sentences, front-loaded with what it does, then the negative constraint, then the usage trigger and the required follow-up call. No filler, and every sentence earns its place.

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 an async, non-destructive run trigger with no output schema, the description supplies everything an agent needs: what it produces (a new processId), how to retrieve results (poll get_optimization_details), and when it is warranted. Nothing material is missing.

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 100%, so the schema already documents all four parameters including required vs optional and the scenarioCount range/default. The description links the concept ('fresh scenario pool') but adds no format or syntax detail beyond what the schema provides, so the baseline of 3 is appropriate.

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 ('re-test a variant') plus resource and scope: head-to-head against the original baseline on a fresh scenario pool. The explicit 'Generates NO new variants — runs only V1 vs the source baseline' distinguishes it cleanly from siblings like apply_variant, regression_test, and simulate_ab_test.

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?

Gives a clear when-to-use condition: 'to confirm whether a winning variant is real signal or sample noise (especially when an exploratory run was small).' It does not explicitly name or exclude an alternative tool, but the triggering scenario is unambiguous enough that an agent can route correctly.

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