stats.ttest_paired

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

Annotations already declare readOnlyHint=true, idempotentHint=true and closed-world, so the safety profile is covered. The description adds value beyond that: df is fixed at n-1, the CI is defined as the 95% interval for (mean a - mean b), and output precision is pinned (t to 6 significant digits, p to 10 digits). It does not state behavior on mismatched lengths or degenerate input, so not a 5.

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?

Four dense sentences, front-loaded with purpose and outputs, then pairing constraints, then tail options, then the sibling disambiguation last. Every sentence carries information, though the digit-precision sentence is the least critical and could be trimmed.

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?

An output schema exists, yet the description still defines the return values and their precision, and it covers the pairing contract and tail options — enough to call the tool correctly. Minor gaps (mismatched-length handling, direction semantics of one-sided tails) keep it from a 5.

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 must carry the burden and largely does: a and b are same-length lists of Decimal strings with at least 2 elements, paired element-by-element, and tail accepts two (default), less, greater — the enum the schema fails to declare. It stops short of explaining which direction 'less' vs 'greater' tests, which is the main remaining ambiguity.

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 (paired-sample t-test on mean differences) and enumerates the exact outputs (t, df(n-1), p_value, ci_95). It also explicitly names the sibling it is not — ttest_two_sample for independent groups — so an agent can route correctly without reading 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?

Gives the selecting condition for this tool (same-subject before/after, paired observations) and an explicit exclusion with the alternative named: '서로 다른 대상의 두 집단에는 ttest_two_sample 을 쓴다.' Nothing is left to inference.

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