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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world). The description adds that results come from a real algorithm engine rather than LLM generation and that the payload is pairwise P values, which is useful since no output schema exists. It omits the multiplicity adjustment method, which materially affects how the returned P values should be read.

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?

Two short, front-loaded sentences that state the method, the trigger, and the return value with no filler. The bracketed opening largely restates the annotation title, which is minor redundancy.

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 single-parameter statistical test with no output schema, the description does state what comes back (pairwise P values). It leaves out the adjustment method and any prerequisite on group sizes, details that matter for correctly interpreting a Dunn 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?

Only one parameter (groups) exists and schema description coverage is 100%, with the schema already documenting the {group name: [values...]} shape. The description adds no constraint on minimum group count, equal-format requirements, or missing-value handling, so the baseline 3 applies.

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 a specific method and resource — Dunn multi-group non-parametric pairwise comparison — and anchors it to the Kruskal-Wallis workflow, which implicitly separates it from parametric post-hoc siblings like act_tukey_hsd. It never names those siblings explicitly, so an agent must infer the boundary.

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 trigger condition is stated clearly: use this after a Kruskal-Wallis test when multi-group pairwise comparisons are needed. There is no explicit when-not guidance or named alternative (e.g. Tukey HSD for parametric data), which keeps it just short of a 5.

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