kruskal_wallis

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

Annotations already convey readonly, idempotent, nondestructive behavior. The description adds meaningful extra context: the test ranks combined data, avoids normality assumptions, and its result is non-explanatory about which group differs. This goes beyond annotations and helps the agent set expectations.

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 compact and well-structured into exactly three useful sentences: what it is, when to use it, and how to interpret results. Every sentence earns its place without redundant or promotional language.

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 statistical hypothesis-testing tool without an output schema, this description provides the necessary conceptual framing: purpose, timing, and interpretation. It could mention return values explicitly, but the description plus the schema is enough for an agent to safely select and invoke the tool.

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 parameters are already well documented: groups is a list of observation lists, alpha is a defaulted significance level. The description adds conceptual context for the test but not additional parameter-specific detail, which matches the schema-heavy baseline.

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 clearly identifies the tool as the non-parametric alternative to one_way_anova and states that it tests whether all groups are drawn from the same distribution. It also distinguishes the tool's scope by mentioning ranking of combined data and the caveat that a significant result does not identify which group differs.

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 tells the agent when to use this tool: when one_way_anova's own small-df warning makes normal-theory results suspect. It provides a clear comparison with a named sibling tool, though it does not explicitly mention the two-group alternative (e.g., mann_whitney_u) or state direct exclusions.

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