stats.ttest_two_sample

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

Annotations already cover the read-only/idempotent safety profile, and the description adds real behavior: the a−b direction of the ci_95 interval, the ≥2 value minimum per sample, and the fact that Welch's df can be fractional. It does not discuss assumptions (independence, approximate normality) that affect validity of the result.

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?

Information-dense with no filler; each sentence covers outputs, input types, parameter behavior, or the sibling alternative. It shifts from return values to parameters to output typing a bit abruptly, and the closing 'df는 문자열이다' sits oddly after the tail list.

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?

With an output schema present, the description does not need to enumerate return fields, yet it names the key ones; inputs, defaults, and the alternative tool are all covered. The main omission is the statistical assumption context that determines whether a t-test is the right choice at all.

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 0%, so the description carries the full burden — and it does: a/b are Decimal strings with a minimum of two values, equal_var maps False→Welch and True→Student, and tail's allowed values (two/less/greater) with default are spelled out even though the schema declares no enum. This is meaning the schema alone does not convey.

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 statistic ('독립 두 표본의 평균 차이를 t-검정으로 판정') plus the exact statistics returned, and explicitly contrasts with the sibling ttest_paired for before/after designs. An agent can distinguish it from ttest_one_sample and ttest_paired without opening either schema.

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?

Explicitly routes the agent to ttest_paired for repeated measurements on the same subject, and the stated default equal_var=False signals Welch as the recommended path. It does not mention when a nonparametric sibling such as mann_whitney_u would be preferable, so the exclusion set is incomplete rather than absent.

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