mann_whitney_u

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

Annotations already declare readOnlyHint and destructiveHint, so safety is covered. The description adds valuable behavioral context: statistic is U for sample a and returns the same result shape as parametric tests (statistic, p_value, citation, warnings), which explains expected output without contradiction.

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 yet thorough: usage condition, mechanism, statistic meaning, effect size pairing, and return shape. Each sentence earns its place, front-loads the key differentiator, and has no fluff.

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?

With no output schema, the description covers the essential aspects: when to use, what it does, what statistic to expect, how to pair with effect size, and the result shape. It's comprehensive for a hypothesis test with clear parameters and annotations.

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 100% with all parameters (a, b, alpha) described. The description doesn't add much beyond schema; it refers to 'sample a' and 'sample b' which mirrors the schema. It adds the meaning of U but not directly about parameters. Baseline 3 is appropriate given high schema coverage.

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 this as the non-parametric alternative to two_sample_t_test, stating it tests whether values from sample a are systematically larger/smaller than from sample b via ranking. It distinguishes from siblings by name-dropping two_sample_t_test and rank_biserial_correlation, making the purpose unambiguous.

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?

Explicitly states when to use: when the two_sample_t_test's small-n warning makes normal-theory suspect, or data is ordinal/skewed. It also recommends pairing with rank_biserial_correlation for effect size, providing clear guidance on alternatives and complementary tools.

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