stats.kruskal_wallis

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

The annotations already cover read-only, idempotent, closed-world behavior, so the additional detail here carries weight: output precision formats (6 significant digits for H, 10-digit string for p) and the absence of post-hoc tests are both facts the agent could not get from the annotations. Nothing contradicts the declared safety profile.

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?

Purpose and return values are front-loaded in the first sentence, with input contract, precision, and the scope limitation following in a logical order. Four dense sentences with no filler, though the return-value sentence partly duplicates what the output schema already supplies.

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 specifies formats, and it adds the input contract, the assumption profile, and the scope boundary. For a single-parameter statistical test, an agent has everything required to call it correctly and interpret the result.

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% and groups is an untyped nested array, but the description fully defines it: a list of per-group Decimal string lists, at least two groups, at least one observation each. That is exactly the missing contract, so no further lookup is needed.

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 names the exact test (rank-based Kruskal-Wallis H), the quantity it judges (differences in distribution location across independent groups), and the outputs it returns (h_stat, p_value, df). That specificity is enough to distinguish it from the parametric stats.anova_oneway and the two-group stats.mann_whitney_u, though it never names a sibling explicitly.

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 the key selection condition (no normality assumption required), which implies the switch from ANOVA, and states an explicit exclusion: no post-hoc pairwise comparison. It stops short of naming an alternative tool for follow-up or the two-group case.

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