mann_whitney_test

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

With no annotations, the description carries the full burden. It discloses the non-parametric nature, the comparison of distributions, and the strict requirement of two groups. However, it does not detail the output structure or error conditions. Since an output schema exists, the return type is covered, but the description omits any caveats like independence assumptions or handling of missing values, making the transparency adequate but not rich.

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 each sentence contributes: the core definition, the non-parametric/sample-size constraint, when to use it, and a concrete example. No redundant phrases, and the structure is logical.

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?

The description, combined with the output schema, covers the essential aspects: purpose, usage, and a limiting condition. The main missing piece is the df_name parameter semantics, but since it is optional and likely defaults to a current dataframe, this is a minor omission. Overall, it is sufficiently complete for an agent to select and invoke the tool correctly in most cases.

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 must compensate. It clarifies 'column' as a numeric column and 'group_column' as the grouping via the example. However, 'df_name' is not explained at all, and the example omits it, leaving ambiguity about whether it is a dataframe name or something else. This is a significant gap given the lack of schema descriptions.

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 states the tool is a Mann-Whitney U test, explicitly describing it as a non-parametric alternative to the t-test that compares distributions of a numeric column across two groups. This distinguishes it from siblings like ttest_independent, anova_test, and normality_test. The example adds concrete usage context.

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 gives explicit when-to-use guidance: 'Use when normality_test indicates non-normal data' and includes a constraint: 'Requires exactly 2 groups.' This sets clear boundaries and implies alternatives for other cases, but does not explicitly name alternatives (e.g., Kruskal-Wallis for >2 groups), so it falls 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.