sequential_two_sample_mean_test

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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context: the always-valid guarantee, safety to re-call after each observation, the repeated-checking failure mode, and the return payload (effect estimate, standard error, mixture likelihood ratio, always-valid p-value, assumption warnings).

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?

The description is front-loaded with the core purpose and then builds through contrast, usage guidance, return values, and param guidance. It is longer than strictly necessary, especially the parenthetical about naive_peeking_inflation, but each sentence contributes useful decision-relevant information.

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 no output schema, the description wisely covers the return values. It also addresses the key selection context (repeated checking), the main alternative (two_sample_t_test), and tau tuning. It could be slightly more explicit about data-shape expectations or assumptions, but the current detail is adequate for correct invocation.

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 baseline is 3. The description adds value by explaining tau practically: 'tau does not need to be exact -- reuse the minimum-detectable-effect you'd otherwise plug into sample_size_for_two_sample_t_test.' This helps an agent choose a real tau value rather than treating it as an exact threshold.

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 opens with a specific verb and resource: 'Always-valid test of whether two groups' means differ.' It clearly differentiates itself from two_sample_t_test by emphasizing repeated checking and sequential safety, so an agent can distinguish this from its main sibling without reading schemas.

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 explicitly says when to use this tool: 'Use this instead of two_sample_t_test whenever a result will be (or already has been) checked more than once as data accumulates.' It also names the alternative and explains the failure mode of repeated peeking, giving clear decision criteria.

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