Skip to main content
Glama

BRAINIAC A/B Testing & Experimentation Statistics

Run a frequentist A/B test scorecard

experimentation_ab-test-frequentist
Read-onlyIdempotent

Two-arm A/B scorecard for conversion (two-proportion z) or continuous (Welch t) metrics: absolute and relative lift, confidence intervals, p-value and significance. Pure computation on supplied aggregates. Price $0.02 USDC. POST /api/v1/experimentation/ab-test-frequentist. 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": {
      "metricType": "<metricType>",
      "control": "<control>",
      "treatment": "<treatment>"
    },
    "name": "experimentation_ab-test-frequentist"
  }
}

Input Schema

NameRequiredDescriptionDefault
alphaNoalpha, number. Required.
controlYescontrol, value. Required.
treatmentYescontrol, value. Required.
metricTypeYesmetricType, string, one of proportion, mean. Required.
alternativeNoalternative, string, one of two-sided, greater, less. Required.two-sided

Output Schema

NameRequiredDescriptionDefault
testNotest. String.
pValueNopValue. Number.
sourcesNosources. Array.
statisticNostatistic. Number.
absoluteCiNoabsoluteCi. Array.
relativeCiNorelativeCi. Array.
controlRateNocontrolRate. Number.
limitationsNolimitations. Array.
significantNosignificant. Boolean.
absoluteLiftNoabsoluteLift. Number.
relativeLiftNorelativeLift. Number.
treatmentRateNotreatmentRate. Number.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond readOnlyHint/idempotent, the description discloses concrete operational facts an agent cannot get from annotations: the $0.02 USDC price, the endpoint, and crucially that an unpaid call returns x402 payment terms and does NOT execute. That failure-mode disclosure is exactly the kind of context annotations don't carry.

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?

Five short sentences, capability first, then computation guarantee, then pricing/auth detail. Efficient overall; the endpoint path and price could arguably live in structured metadata, but they are not wasteful given how central payment is to invoking this tool correctly.

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?

With an output schema covering return values and readOnly annotations covering safety, the description fills the remaining gaps: what is computed, that it is pure computation on aggregates, the cost, and the unpaid-call behavior. Minor omission: the control/treatment shape must match metricType, which is only inferable.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description earns extra credit by mapping metricType values to test procedures (proportion → two-proportion z, mean → Welch t), which is semantic guidance the schema's raw enum does not supply. It does not mention the alternative parameter's one-sided options.

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 names a specific resource (a two-arm A/B scorecard) and enumerates the statistical outputs it produces: two-proportion z for conversion, Welch t for continuous, absolute/relative lift, CIs, p-value, significance. The word 'frequentist' plus the precise test names give an agent a clean basis for telling this apart from the bayesian or sequential siblings.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: 'frequentist' and 'two-arm' signal the paradigm, and 'Pure computation on supplied aggregates' signals there is no data fetching, but the description never says when to pick this over experimentation_bayesian-ab or experimentation_sequential-test, nor any exclusion.

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