Skip to main content
Glama
mrnh

rigor-mcp

by mrnh
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

recommend_test

Read-onlyIdempotent

Answer a few data characteristics to get the right statistical test to call, with reasoning, alternatives if assumptions are shaky, and companion analyses. Pure decision logic—no statistics computed.

Instructions

Not sure which rigor tool fits your question? Answer a few characteristics of the data and get back which tool to call, why, what to call instead if this test's assumptions look shaky, and what to run alongside it (an effect size, a power calculation, a natural follow-up). Every test in this package already documents this guidance in its own docstring for the sibling comparisons it knows about -- this tool exists so you don't have to have already read every other tool's docstring to find the one relevant cross-reference. Pure decision logic, no statistics computed here.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pairedNofor n_groups=2 (continuous/rank_or_ordinal/proportion): were the same subjects measured twice, rather than two independent groups?
n_groupsNo1 = one sample vs. a hypothesized value; 2 = two groups/conditions; 3+ = three or more groups. Ignored when testing_association=true.
outcome_typeYeswhat kind of thing is being compared/measured: "continuous" (means), "proportion" (rates), "count_or_category" (category counts / contingency tables), or "rank_or_ordinal" (ordinal data -- always routed to a rank-based test)
small_or_skewedNois the sample small, visibly skewed, or outlier-heavy? nudges toward the non-parametric alternative
checked_repeatedlyNowill this result be checked more than once as data accumulates (e.g. a live experiment's dashboard) rather than analyzed once against a pre-committed sample size? routes to a peeking-safe sequential_* tool instead, where one exists
testing_associationNothis is "does x relate to/predict y" for two continuous or ranked variables, not a group comparison -- routes to correlation/regression instead
two_categorical_variablesNofor outcome_type="count_or_category": testing association between two categorical variables (a contingency table) rather than counts against an expected distribution?

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • addedInput schema / properties / checked_repeatedly
      Added value: +{
+  "default": false,
+  "description": "will this result be checked more than once as data accumulates (e.g. a live experiment's dashboard) rather than analyzed once against a pre-committed sample size? routes to a peeking-safe sequential_* tool instead, where one exists",
+  "title": "Checked Repeatedly",
+  "type": "boolean"
+}
  2. Addedv0.3.0

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds that it is 'pure decision logic' and 'no statistics computed here,' clarifying it does not perform calculations. It also discloses the content of the output (which tool, why, alternatives, and accompanying analyses). This provides useful behavioral context beyond the safety hints.

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?

The description is front-loaded with the use case ('Not sure which rigor tool fits your question?') and clearly structures what the tool returns. While it includes a slightly verbose explanation about other docstrings, it remains readable and purposeful, earning a 4 rather than a 5.

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

Completeness4/5

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

Given no output schema and seven parameters, the description sufficiently explains what the tool returns (which tool, why, alternatives, and accompanying analyses) and its decision-only scope. It does not specify the exact output format or edge cases (e.g., no matching tool), so it falls short of complete, but is still strong.

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?

The input schema covers 100% of parameters with detailed descriptions, so the tool description does not need to add parameter-level meaning. The description itself does not mention parameters, aligning with the baseline of 3 for high schema coverage.

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?

The description states a clear purpose: to recommend a rigor tool based on data characteristics. It explicitly differentiates from sibling statistical tests by stating 'Pure decision logic, no statistics computed here.' The verb 'recommend' and resource 'which rigor tool' are specific, making the tool's role unambiguous.

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

Usage Guidelines4/5

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

The description gives a clear when-to-use signal: 'Not sure which rigor tool fits your question?' It implies the tool is for users who lack certainty and explains it exists to avoid reading all other docstrings. However, it does not explicitly state when not to use it or name alternative tools, so it stops short of full exclusion guidance.

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

Deploy Server

Other Tools