Skip to main content
Glama
gdavos007

Statistical Testing MCP Server

by gdavos007

run_test

Execute Welch's t-test or two-proportion z-test on a deterministic bounded table extract with specified outcome and grouping columns, group values, and significance threshold.

Instructions

Run one approved statistical test on a deterministic bounded table extract.

Use Welch welch_t_test for a two-sided independent-samples comparison of numeric means without an equal-variance assumption. Use the two-proportion two_proportion_z_test for a comparison of binary success proportions, and always provide the explicit success value; the server never guesses it. Both tests require a conservative table identifier, outcome and grouping columns, exactly two group values, alpha between 0 and 1, and an optional row cap. The configured hard row limit always applies; truncation and first-N bias are reported. Rows with null outcomes or groups are excluded and counted. Welch rejects non-numeric or non-finite outcomes and needs two observations per group. The proportion test requires an exactly binary selected outcome and at least five successes and five failures per group. Do not use either test for paired/repeated observations or causal conclusions. Results contain maintained-library statistics and p-values, effect sizes, assumptions, warnings, and audit metadata. Significance does not establish causality or business importance.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
alphaYesSignificance threshold strictly between 0 and 1
tableYesConservative table identifier
test_idYeswelch_t_test or two_proportion_z_test
max_rowsNoOptional requested row cap; the server hard limit always applies
group_valuesYesExactly two group values
success_valueNoRequired explicit success value for two_proportion_z_test
outcome_columnYesNumeric continuous outcome column
grouping_columnYesColumn containing independent groups

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

No annotations provided, so description carries full burden. It discloses that null rows are excluded and counted, Welch rejects non-numeric outcomes, results include warnings and audit metadata, hard row limit applies, and reports truncation/first-N bias.

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?

Description is comprehensive but somewhat lengthy (single paragraph). It packs all necessary information, though could be slightly more concise by splitting into sections. No unnecessary repetition.

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

Completeness5/5

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

Given output schema exists, description doesn't need return values. It covers assumptions, limitations, warnings, audit metadata, and edge cases (nulls, caps). Complete for a statistical test tool.

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

Parameters5/5

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

Input schema has 100% coverage, but description adds significant meaning beyond schema descriptions. It explains test_id options, required group_values count, explicit success_value for proportion test, and row cap behavior.

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?

Description clearly states it runs an approved statistical test (Welch t-test or two-proportion z-test) on a bounded table extract. It distinguishes from sibling tools (list_tables, profile_table) by specifying its unique purpose of performing hypothesis tests.

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?

Explicitly provides when to use each test: Welch for two-sided numeric means comparison, two-proportion z-test for binary proportions. Also states when not to use (paired/repeated observations, causal conclusions) and includes conditions like required sample sizes.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gdavos007/stat-agent-mcp-spec'

If you have feedback or need assistance with the MCP directory API, please join our Discord server