Skip to main content
Glama

BRAINIAC A/B Testing & Experimentation Statistics

Measure cumulative impact against a long-term holdout

experimentation_holdout-impact
Read-onlyIdempotent

Exposed-versus-holdout impact with confidence interval and p-value, plus diluted population-level impact for partial exposure. Price $0.01 USDC. POST /api/v1/experimentation/holdout-impact. 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>",
      "holdout": "<holdout>",
      "exposed": "<exposed>"
    },
    "name": "experimentation_holdout-impact"
  }
}

Input Schema

NameRequiredDescriptionDefault
alphaNoalpha, number. Required.
exposedYesholdout, value. Required.
holdoutYesholdout, value. Required.
metricTypeYesmetricType, string, one of proportion, mean. Required.
exposureRateNoexposureRate, number, from any to 1. Optional.

Output Schema

NameRequiredDescriptionDefault
ciNoci. Array.
pValueNopValue. Number.
sourcesNosources. Array.
dilutedCiNodilutedCi. Array.
limitationsNolimitations. Array.
significantNosignificant. Boolean.
dilutedImpactNodilutedImpact. Number.
absoluteImpactNoabsoluteImpact. Number.
relativeImpactNorelativeImpact. Number.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: the $0.01 USDC price, the x402 payment flow, and the crucial fact that an unpaid call returns payment terms and does not execute — information an agent cannot get from the schema or annotations.

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?

Three compact sentences lead with what is computed, then cost, endpoint, and payment failure mode. It is appropriately front-loaded and free of filler, though the bare POST path is terse enough to read as boilerplate.

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 handling return values, full schema coverage of parameters, and annotations covering safety, the description carries the remaining burden well by disclosing payment gating. The missing piece is when-to-use guidance relative to the statistically overlapping siblings.

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?

Schema description coverage is 100%, so all five parameters are documented in the schema itself and the baseline is 3. The phrase 'diluted population-level impact for partial exposure' gives a functional hint about exposureRate that the schema merely labels as an optional number, but it does not explain metricType or the two input shapes.

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?

The description names a specific computation — exposed-versus-holdout impact with confidence interval, p-value, and diluted population-level impact for partial exposure — which is far more than a restatement of the name. It does not, however, explicitly contrast itself with sibling tools such as the frequentist or Bayesian A/B tests, so an agent must infer the distinction from the 'long-term holdout' framing.

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

Usage Guidelines2/5

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

There is no explicit statement of when to reach for this tool instead of the A/B-test or lift siblings. The only conditional information is 'for partial exposure', which hints at the exposureRate scenario but is about output interpretation rather than tool selection.

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