Skip to main content
Glama

Stat Bayes Ttest

stat_bayes_ttest

Run a Bayesian t-test to quantify evidence for the null and alternative hypotheses, especially when interpreting non-significant results or comparing groups.

Instructions

Bayesian t-test — quantifies evidence for the null as well as the alternative.

WHEN TO USE

  • When a non-significant result needs interpreting. A frequentist p > .05 does not mean the null is true; BF₀₁ directly quantifies evidence for it.

  • When the researcher wants to state "the groups are comparable".

WHEN NOT TO USE

  • As a way to find significance after a non-significant t-test. Decide on the analysis approach in advance.

Report BF₁₀ and BF₀₁, and state the prior scale (r).

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>",
      "group": "<group>"
    },
    "name": "stat_bayes_ttest"
  }
}

Input Schema

NameRequiredDescriptionDefault
rNo
dvYes
nameYes
groupYes
pairedNo
subjectNo
alternativeNotwo-sided

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are supplied, so the description must carry the full behavioral burden. It does well on output expectations ('Report BF₁₀ and BF₀₁, and state the prior scale (r)') and prior sensitivity, and the dependence on a prior scale is a real behavioral detail. It does not state the assumptions of the test, how it handles the paired case, or what happens with unbalanced groups.

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

Conciseness5/5

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

Front-loaded one-line purpose followed by labeled sections and a reporting requirement. Every line is actionable, and the reporting sentence doubles as a useful instruction rather than filler.

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, so that gap is excused, and the when/when-not guidance is strong for the default case. But a 7-parameter tool with no annotations and 0% schema coverage leaves the paired/subject mode and the alternative options unexplained, which is a material incompleteness for correct invocation.

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?

There are 7 parameters at 0% schema description coverage, so the description must compensate and it mostly does not. Only 'r' (prior scale) is given meaning; 'name', 'dv', 'group', 'paired', 'subject', and 'alternative' are never mentioned, leaving the agent to guess at paired/subject interaction and the meaning of 'alternative'.

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 first line names the specific method ('Bayesian t-test') and its distinguishing capability ('quantifies evidence for the null as well as the alternative'). This immediately separates it from the frequentist sibling stat_ttest without needing to open either schema.

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?

Explicit WHEN TO USE section names the trigger condition (a non-significant result needing interpretation, or a claim of comparability) and WHEN NOT TO USE names the anti-pattern (fishing for significance after a p > .05). No inference is required to pick this tool.

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