Skip to main content
Glama

BRAINIAC Statistics & Quality Engineering

Run a nonparametric test

statistics_nonparametric-tests
Read-onlyIdempotent

Mann-Whitney U, Wilcoxon signed-rank, Kruskal-Wallis, Friedman and sign tests with average-rank ties, exact p-values for samples up to 50 and tie-corrected normal approximations. Price $0.03 USDC. POST /api/v1/statistics/nonparametric-tests. An unpaid call returns the x402 payment terms and does not run.

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": {
      "test": "<test>"
    },
    "name": "statistics_nonparametric-tests"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNox, array. Optional.
yNoy, array. Optional.
mu0Nomu0, number. Required.
testYestest, string, one of mann_whitney, wilcoxon_signed_rank, kruskal_wallis, friedman, sign. Required.
exactNoexact, value. Required.auto
blocksNoblocks, array. Optional.
groupsNogroups, array. Optional.

Output Schema

NameRequiredDescriptionDefault
nNon. Object.
methodNomethod. String.
pValueNopValue. Number.
sourcesNosources. Array.
statisticNostatistic. Number.
droppedRowsNodroppedRows. Number.
limitationsNolimitations. Array.
tieCorrectionNotieCorrection. Boolean.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior4/5

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

Well beyond the annotations, the description discloses the pricing ($0.03 USDC), the endpoint, and critically that an unpaid call returns x402 payment terms without running — an agent that omits payment would otherwise misread the response. It also states statistical behavior (average-rank ties, exact p-values capped at n=50, tie-corrected normal approximation) that the annotations do not cover. It does not describe output shape, but an output schema exists to carry that.

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?

Three sentences, front-loaded with the capability set, then commercial and protocol facts. No filler, and the most surprising behavior (unpaid calls do not execute) is placed last for emphasis. Structurally sound.

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?

For a multi-test dispatch tool with seven parameters and an output schema, the description covers method selection, p-value behavior, and payment flow adequately. The notable gap is the mapping of parameters to tests, which an agent must reverse-engineer from the schema enum and array names. It is usable but leaves real ambiguity for a tool this configurable.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline is 3. The description does clarify the meaning of the `exact` parameter by noting exact p-values apply only up to samples of 50 and that ties are handled by average ranks. However, with five alternative tests and seven parameters, the highest-value missing information is which parameters each test consumes (x/y vs groups vs blocks), and that is absent.

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

Purpose4/5

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

The description names the five specific procedures (Mann-Whitney U, Wilcoxon signed-rank, Kruskal-Wallis, Friedman, sign) plus its tie-handling and p-value strategy, which clearly separates it from the parametric siblings like statistics_t-test and statistics_anova. It reads as a capability list rather than an explicit scope statement, but an agent can still identify the tool unambiguously.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance. The description never says to prefer this over statistics_t-test/statistics_anova when normality assumptions fail, nor does it explain which design (paired, two-sample, k-group, blocked) maps to which named test. The only inference available is from the enumerated test names themselves.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources