stats.descriptive

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

Annotations already declare readOnly, idempotent, closed-world behavior, so the safety profile is covered. The description adds genuinely new behavior: q1/q3 use numpy linear interpolation, computation is float64, and results are returned as 10-significant-digit strings — details an agent cannot infer from annotations or schema.

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 short sentences, each carrying distinct information: outputs, input constraint, ddof semantics, and percentile/precision method. The core purpose is front-loaded with no 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?

For a two-parameter, output-schema-backed calculation tool this is nearly complete: input format, ddof meaning, numerical method, and output precision are all covered. Only edge-case behavior (non-numeric strings, rounding of the reported stdev) is left unstated, which is minor given the output schema.

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 0%, so the description carries the full burden and does so: values must be Decimal strings with at least two elements, and ddof defaults to 1 for sample variance/stdev while 0 yields population values. Both parameters gain meaning that the bare schema does not provide.

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 uses a specific verb (계산한다) plus the exact resource (기술통계량) and enumerates all nine returned statistics (n, mean, median, variance, stdev, min, max, q1, q3). That enumeration clearly separates it from the inference-oriented siblings such as stats.ttest_one_sample or stats.ci_mean.

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?

It gives useful in-tool guidance (ddof=1 for samples, ddof=0 for full population data), but never states when to pick this tool over a sibling or that no alternative exists. Usage is implied by the statistic list rather than explicitly framed.

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