Skip to main content
Glama

Persuasion Taxonomy

Read an A/B test result

read_ab_test_result
Read-onlyIdempotent

Read the result of an A/B test. You get each version's conversion rate and lift, whether the difference is statistically significant, the confidence interval, and the chance each version really beats the original. It also warns you about the things that make a test result lie. Those include too few conversions, traffic that didn't split the way it should (a sample ratio mismatch), stopping the moment it looked good, and testing too many versions at once. It answers questions like "did my test win?", "is this significant?", "which version won?" or "should I keep it running?"

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": {
      "versions": "<versions>"
    },
    "name": "read_ab_test_result"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionNoThe reader question the versions answered in different ways.
versionsYesEach version with its visitors and conversions. Put the original, the control, first.
confidenceNo
intended_splitNoHow you meant to split the traffic, like [50, 50]. The default is an even split.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only establish that this is a safe, idempotent, closed-world read; the description goes beyond them by enumerating the returned statistics and disclosing that the tool emits warnings for invalid results (low conversions, sample ratio mismatch, peeking, too many variants). That pitfall-detection behavior is valuable and not derivable from any structured field. It does not cover failure modes (e.g., what happens with malformed versions) or output shape beyond a prose list.

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-loaded with the core action and output inventory, then the warning behavior, then query phrasings. The pitfall list and the four example questions each add a little redundancy, but nothing is padded or vague enough to obstruct an agent.

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 no output schema, the description carries the burden of describing returns and does so adequately, and the annotations cover the safety profile. The gap is parameter-level behavior — a calling agent gets no explanation of how `confidence` and `intended_split` affect the reported verdicts or warnings.

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 75%, so the schema already documents the question enum, versions, intended_split and the control-first ordering. The description adds no parameter meaning at all — notably it never mentions that `confidence` changes the significance verdict or how `intended_split` drives the sample-ratio-mismatch warning, which is exactly the kind of semantics worth restating.

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?

Names a specific verb and resource ("Read the result of an A/B test") and immediately scopes what it returns: conversion rate, lift, significance, confidence interval, chance to beat control. This is clearly the analysis sibling to plan_ab_test rather than a planning or copy tool, so an agent can distinguish it without opening the schema.

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

Usage Guidelines4/5

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

The closing sentence maps natural user questions ("did my test win?", "is this significant?", "should I keep it running?") directly to this tool, which is strong implied when-to-use guidance. It stops short of stating prerequisites (the test must already have data) or naming plan_ab_test as the alternative to use before a test exists.

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.