Skip to main content
Glama

BRAINIAC A/B Testing & Experimentation Statistics

Apply CUPED variance reduction and test the adjusted effect

experimentation_cuped-adjust
Read-onlyIdempotent

CUPED adjustment with a pre-experiment covariate on unit-level data: theta, variance reduction, and Welch tests on raw and adjusted values. Price $0.03 USDC. POST /api/v1/experimentation/cuped-adjust. 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": {
      "units": "<units>"
    },
    "name": "experimentation_cuped-adjust"
  }
}

Input Schema

NameRequiredDescriptionDefault
alphaNoalpha, number. Required.
unitsYesunits, array. Required.

Output Schema

NameRequiredDescriptionDefault
rawNoraw. Object.
thetaNotheta. Number.
groupsNogroups. Object.
sourcesNosources. Array.
adjustedNoadjusted. Object.
limitationsNolimitations. Array.
varianceReductionNovarianceReduction. Number.
unitsWithoutCovariateNounitsWithoutCovariate. 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 read-only, idempotent, and non-destructive behavior, and the description adds genuinely new operational context: a $0.03 USDC price, the POST endpoint, and the fact that an unpaid call returns x402 payment terms instead of executing. That payment-gating disclosure is exactly the kind of behavior an agent cannot get from annotations. It does not cover data preconditions (e.g., what happens with null x values or minimum sample requirements).

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, front-loaded with the core purpose, then cost, then endpoint and payment behavior. No filler. The middle sentence is a fragment list ('theta, variance reduction, and Welch tests') that reads as terse rather than polished, but it conveys information efficiently.

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?

An output schema exists, so return values need no explanation, and the description covers purpose, cost, transport, and the payment-failure path. For a two-parameter statistical tool that is close to sufficient. The remaining gap is input expectations — whether x is required for a meaningful adjustment and any minimum data requirements.

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 would be 3, but the schema text is largely mechanical ('x, number. Optional.'). The description supplies the missing semantics: x is the pre-experiment covariate, the data is unit-level, and the outputs are theta plus adjusted and raw Welch tests. It still does not explain how alpha is applied or the role of the group field.

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 technique and resource: CUPED adjustment using a pre-experiment covariate on unit-level data, and names the concrete outputs (theta, variance reduction, Welch tests on raw and adjusted values). That is far more informative than the title. It stops short of distinguishing itself explicitly from siblings like delta-method-ratio or bayesian-ab, relying on the agent to know what CUPED is.

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?

The phrase 'with a pre-experiment covariate on unit-level data' implies the precondition for using this tool rather than a plain A/B test, but it never says so directly. There is no explicit when-to-use/when-not statement and no named alternative among the many sibling test tools. Usage must be inferred from domain knowledge.

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