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

Annotations show readOnlyHint=false and destructiveHint=false, and the description adds meaningful context beyond them: it is asynchronous ('Returns a new processId; poll get_optimization_details on it for results') and produces no new variants, only a re-run of V1 vs baseline. It doesn't cover permissions or cost beyond what the schema states, but adds solid behavioral value the annotations don't provide.

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 tight sentences, front-loaded with the core action and scope, followed by the distinguishing constraint and the async return mechanism. Every sentence earns its place with zero filler.

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?

No output schema exists, yet the description compensates by explaining the return value (a new processId) and the follow-up call to retrieve results. Combined with full schema coverage and clear annotations, an agent has everything needed to invoke and follow up correctly.

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 both required and optional parameters are already fully documented in the schema (including scenarioCount's range and cost note). The description adds the 'V1 vs baseline' framing but no new parameter-level meaning, so baseline 3 applies.

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 and resource ('Re-test a variant... head-to-head against the original baseline on a fresh scenario pool') and explicitly scopes what it does NOT do ('Generates NO new variants — runs only V1 vs the source baseline'). This distinguishes it from siblings like apply_variant and get_variant_details without requiring schema inspection.

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 clear when-to-use guidance ('to confirm whether a winning variant is real signal or sample noise, especially when an exploratory run was small'). It does not name specific alternative tools or an explicit when-not, but the condition for use is unambiguous.

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