Skip to main content
Glama

Stat Nonparametric 2

stat_nonparametric_2

Run Mann-Whitney U or Wilcoxon signed-rank tests for two-group comparisons when normality is not assumed, and report rank-biserial correlation effect size.

Instructions

Mann-Whitney U (independent) or Wilcoxon signed-rank (paired) — two groups, no normality assumption.

WHEN TO USE

  • Ordinal outcomes.

  • Continuous outcomes that are badly non-normal with small n.

  • Outliers that cannot be justified for removal.

  • Any time the mean is not a meaningful summary of the data.

WHEN NOT TO USE

  • Three or more groups → stat_nonparametric_k.

  • When the data are normal: the parametric test is more powerful, and using ranks discards information.

Report the rank-biserial correlation (RBC) as the effect size — the p-value alone says nothing about magnitude.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "dv": "<dv>"
    },
    "name": "stat_nonparametric_2"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
dvYes
nameYes
groupNo
pairedNo
subjectNo
alternativeNotwo-sided

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the two variants, that ranks discard information, and that the rank-biserial correlation is reported as effect size with a warning that p alone is insufficient. It stops short of stating other assumptions (independence, similar distribution shapes for Mann-Whitney) or how paired mode changes data requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the tests and the design constraint, then cleanly sectioned into WHEN TO USE / WHEN NOT TO USE with the effect-size note at the end. The final catch-all bullet about the mean is slightly redundant with earlier bullets but otherwise every line earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema covers return values and the guidance covers test selection well, but for an 8-parameter tool with zero schema documentation the description leaves the agent guessing about how to wire the arguments together. Adequate for choosing the test, insufficient for invoking it confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% across 8 parameters, so the description must compensate and largely does not. It hints at a paired/independent switch and at grouping, but never explains what x, y, dv, name, group, subject, or alternative mean or which combination is required — a critical gap since paired=TRUE presumably needs a subject column.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names the two concrete tests (Mann-Whitney U for independent, Wilcoxon signed-rank for paired), the design constraint (two groups), and the assumption it avoids (normality). It is immediately distinguishable from stat_nonparametric_k, which is explicitly cited as the alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit WHEN TO USE bullets (ordinal outcomes, badly non-normal continuous data with small n, unremovable outliers, non-meaningful mean) and an explicit WHEN NOT TO USE section that routes 3+ groups to stat_nonparametric_k and normal data to the parametric test. This is the model of when/when-not guidance.

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