Microapp

ab-test-calculator

Read-onlyIdempotent

Two-proportion z-test for A/B conversion-rate experiments. Returns each arm's rate and 95% Wald confidence interval, the absolute and relative lift, the z statistic, the two-tailed p-value, and a significance decision at the given alpha (default 0.05).

Input Schema

TableJSON Schema

Name	Required	Description
`alpha`	No	Significance threshold (default 0.05). p < alpha declares a statistically significant difference. Two-tailed.
`control_visitors`	Yes	Number of unique visitors (or sessions, or impressions — whatever the conversion denominator is) in the control arm. Must be a positive integer.
`variant_visitors`	Yes	Number of unique visitors in the variant arm. Must be a positive integer.
`control_conversions`	Yes	Number of conversions observed in the control arm. Must be a non-negative integer, and cannot exceed control_visitors.
`variant_conversions`	Yes	Number of conversions observed in the variant arm. Must be a non-negative integer, and cannot exceed variant_visitors.

Output Schema

TableJSON Schema

Name	Required	Description
`alpha`	Yes	Significance threshold used (defaults to 0.05).
`winner`	Yes	Which arm has the higher observed rate ('tie' if exactly equal). This is the observed winner regardless of significance — pair it with `significant` to know whether the result is reliable.
`p_value`	Yes	Two-tailed p-value from the standard normal distribution.
`z_score`	Yes	Two-proportion z statistic with pooled standard error.
`control_ci`	Yes	95% Wald confidence interval for the control rate. Bounds are clamped to [0, 1].
`variant_ci`	Yes	95% Wald confidence interval for the variant rate. Bounds are clamped to [0, 1].
`significant`	Yes	True when p_value < alpha. The standard win/no-win decision.
`control_rate`	Yes	Control conversion rate as a proportion in [0, 1].
`variant_rate`	Yes	Variant conversion rate as a proportion in [0, 1].
`absolute_lift`	Yes	Absolute difference in rates: variant_rate − control_rate. Positive means the variant beat the control.
`relative_lift`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

AddedMay 21, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare the tool as read-only, idempotent, and non-destructive, which is reinforced by the description's 'Returns...' phrasing. The description goes beyond annotations by detailing the computed outputs (Wald confidence interval, absolute/relative lift, z statistic, two-tailed p-value, significance decision), giving useful insight into its behavior.

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?

The description is a single, information-dense sentence that efficiently conveys the calculation purpose, the full list of outputs, and the default significance level. No unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of a full output schema and a complete input schema, the description adequately covers the tool's purpose, inputs, and outputs. It also notes the default alpha and the two-tailed nature of the test, providing sufficient context for an AI agent to use the tool correctly.

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?

The input schema provides exhaustive descriptions for all five parameters, including constraints and defaults, achieving 100% coverage. The description only mentions the default alpha (0.05) without adding further parameter semantics, so it provides minimal value beyond what the schema already offers.

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?

The description clearly states the tool's function as a two-proportion z-test for A/B conversion-rate experiments, which is a specific statistical procedure. It also lists the exact outputs (rates, confidence interval, lift, z statistic, p-value, significance decision), making it easy to distinguish from sibling tools like ab-test-sample-size.

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 description clearly indicates the tool is for analyzing A/B conversion-rate experiments, which implies its primary use case. It does not explicitly mention when to use an alternative like ab-test-sample-size, but the context is sufficient for an agent to infer the right scenario.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Microapp tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation4/5

Most tools have distinct purposes. However, 'hex-to-rgb' is redundant with 'color-converter', which already handles hex-to-RGB conversion, causing potential confusion.

Naming Consistency4/5

Names follow a consistent lowercase-with-hyphens style, but vary in pattern (e.g., 'angle-converter', 'average-calculator', 'dedup-lines'). One tool ('internal-do-not-call') deviates from the descriptive norm.

Tool Count2/5

With 46 tools, the server is heavily populated. Many converters could be merged into a generic unit converter, and there is redundancy, making the surface unnecessarily large for a single server.

Completeness4/5

The server covers a broad range of utility domains: converters, text processing, math, cryptography, etc. Minor redundancies exist (e.g., hex-to-rgb vs color-converter), but the set is otherwise comprehensive.

Resources

Need Help?