Skip to main content
Glama

BRAINIAC A/B Testing & Experimentation Statistics

Check A/B guardrail metrics for non-inferiority

experimentation_guardrail-check
Read-onlyIdempotent

One-sided non-inferiority tests of guardrail metrics against caller-supplied relative or absolute margins, with bounds and an overall pass flag. Price $0.02 USDC. POST /api/v1/experimentation/guardrail-check. 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": {
      "metrics": "<metrics>"
    },
    "name": "experimentation_guardrail-check"
  }
}

Input Schema

NameRequiredDescriptionDefault
alphaNoalpha, number. Required.
metricsYesmetrics, array. Required.

Output Schema

NameRequiredDescriptionDefault
allPassNoallPass. Boolean.
metricsNometrics. Array.
sourcesNosources. Array.
limitationsNolimitations. Array.

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 declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely new behavioral facts: a $0.02 USDC charge, the POST endpoint, and crucially that an unpaid call returns x402 payment terms without executing. That last point is exactly the kind of precondition an agent must know. It does not describe failure modes for invalid margins, keeping it below 5.

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?

Three short sentences: capability first, then cost and endpoint, then the payment-gate behavior. No filler, no restatement of the tool name, and the most decision-relevant information is front-loaded.

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 not be explained, and the description nonetheless flags bounds and an overall pass flag. Combined with the payment gating note, an agent has what it needs to call this correctly. Only minor gaps remain around error behavior and how alpha interacts with the pass flag.

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 the baseline is 3. The description adds a little meaning by framing margins as 'caller-supplied relative or absolute' and noting the test is one-sided, which hints at how alpha and marginType are used. It says nothing about the alpha default, the higherIsBetter flag, or the two shapes of control/treatment, so it does not exceed the schema.

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 statistical procedure and resource: 'one-sided non-inferiority tests of guardrail metrics.' That is far more precise than a generic 'run test' phrasing and implicitly separates it from the frequentist/Bayesian A/B siblings. It stops short of explicitly pointing at a sibling alternative, so it lands at a clear-but-undifferentiated 4.

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 only implied: the reader infers this is for checking guardrail metrics for non-inferiority after or alongside an A/B test. There is no statement of when to choose this over experimentation_bayesian-ab or experimentation_sequential-test, and no exclusions. The payment prerequisite is stated, but that is an operational note, not usage guidance.

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