Skip to main content
Glama

BRAINIAC A/B Testing & Experimentation Statistics

Calculate A/B sample size or minimum detectable effect

experimentation_sample-size-mde
Read-onlyIdempotent

Required users per arm and duration for a target minimum detectable effect, or the MDE for a fixed sample, for proportion or mean metrics with power, multi-arm Bonferroni and unequal allocation. Price $0.01 USDC. POST /api/v1/experimentation/sample-size-mde. 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>"
    },
    "name": "experimentation_sample-size-mde"
  }
}

Input Schema

NameRequiredDescriptionDefault
mdeNomde, number. Optional.
armsNoarms, integer, from 2 to 10. Required.
alphaNoalpha, number. Required.
powerNopower, number. Required.
mdeTypeNomdeType, string, one of relative, absolute. Required.relative
nPerArmNonPerArm, integer, from 2 to 9007199254740991. Optional.
baselineNobaseline, number. Optional.
allocationNoallocation, array. Optional.
baselineSdNobaselineSd, number. Optional.
correctionNocorrection, string, one of bonferroni, none. Required.none
dailyUsersNodailyUsers, number. Optional.
metricTypeYesmetricType, string, one of proportion, mean. Required.
alternativeNoalternative, string, one of two-sided, greater, less. Required.two-sided
baselineMeanNobaselineMean, number. Optional.

Output Schema

NameRequiredDescriptionDefault
daysNodays. Number.
nByArmNonByArm. Array.
totalNNototalN. Number.
formulaNoformula. String.
nPerArmNonPerArm. Number.
sourcesNosources. Array.
limitationsNolimitations. Array.
alphaPerComparisonNoalphaPerComparison. Number.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the description's added value is the paid-call behavior: $0.01 USDC and the fact that an unpaid call returns x402 payment terms without running. That is genuinely useful context beyond the structured fields, though nothing is said about rate limits or response latency.

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?

Front-loads the core computation, then pricing, endpoint, and payment failure behavior in short clauses. The opening sentence is somewhat dense and clause-stacked but every part carries information.

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?

For a 14-parameter statistical tool with an output schema and annotations, the description covers purpose, payment mechanics, and endpoint. The main gap is mode-specific parameter requirements, which an agent must infer from optionality in the schema.

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 the baseline is 3, but the description adds conceptual meaning by tying parameters together: metricType drives proportion vs. mean, correction covers Bonferroni for multi-arm designs, allocation covers unequal splits, and dailyUsers/duration linkage. It still does not say which optional parameters become required for each mode (e.g., baseline for proportions, baselineSd for means).

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?

States a specific computation (required users per arm and duration, or MDE for a fixed sample) with the metric families it supports. It is clearly distinguishable from sibling analysis tools, though it does not name any sibling explicitly.

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?

Implies the two usage modes (planning a sample size, or inverting to an MDE for a fixed n) through the phrasing, but gives no explicit when-to-use/when-not guidance relative to siblings like experimentation_ab-test-frequentist or experimentation_sequential-test.

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