Rahul D Sarker: Marketing & RevOps Tools

A/B Test Significance Calculator

ab_test_significance_calculator

Read-onlyIdempotent

Run a two-proportion z-test on an A/B test to get relative uplift and statistical confidence. See the full version at https://rahuldsarker.co/calculators/ab-test-significance-calculator

Input Schema

Name	Required	Description
`currency`	No	ISO 4217 code for money in the result, e.g. "USD", "INR", "EUR", "GBP". Omit to show plain numbers.
`visitorsA`	Yes	Visitors in variant A (control)
`visitorsB`	Yes	Visitors in variant B (test)
`conversionsA`	Yes	Conversions in variant A (control)
`conversionsB`	Yes	Conversions in variant B (test)

Output Schema

Name	Required	Description
`url`	Yes
`kind`	Yes
`tool`	Yes	The calculator tool that produced this result
`notes`	Yes
`title`	Yes
`inputs`	Yes
`compact`	Yes
`metrics`	Yes	Every "Label: value" line of the result; value is the first number on the line
`currency`	Yes
`benchmarks`	Yes	Rule-of-thumb verdicts for the headline numbers
`bookingUrl`	Yes
`calculator`	Yes	Slug of the interactive calculator on rahuldsarker.co

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 30, 2026

addedInput schema / properties / currency

Added value: +{
+  "description": "ISO 4217 code for money in the result, e.g. \"USD\", \"INR\", \"EUR\", \"GBP\". Omit to show plain numbers.",
+  "pattern": "^[A-Za-z]{3}$",
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "benchmarks": {
+      "description": "Rule-of-thumb verdicts for the headline numbers",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "band": {
+            "type": "string"
+          },
+          "display": {
+            "type": "string"
+          },
+          "metric": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "read": {
+            "type": "string"
+          },
+          "segment": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "source": {
+            "type": "string"
+          },
+          "target": {
+            "type": "string"
+          },
+          "tone": {
+            "enum": [
+              "good",
+              "ok",
+              "warn",
+              "bad"
+            ],
+            "type": "string"
+          },
+          "value": {
+            "type": "number"
+          }
+        },
+        "required": [
+          "metric",
+          "name",
+          "value",
+          "display",
+          "band",
+          "tone",
+          "read",
+          "target",
+          "segment",
+          "source"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "bookingUrl": {
+      "type": "string"
+    },
+    "calculator": {
+      "description": "Slug of the interactive calculator on rahuldsarker.co",
+      "type": "string"
+    },
+    "compact": {
+      "type": "boolean"
+    },
+    "currency": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "inputs": {
+      "additionalProperties": {},
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "kind": {
+      "const": "calculator",
+      "type": "string"
+    },
+    "metrics": {
+      "description": "Every \"Label: value\" line of the result; value is the first number on the line",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "display": {
+            "type": "string"
+          },
+          "label": {
+            "type": "string"
+          },
+          "unit": {
+            "anyOf": [
+              {
+                "enum": [
+                  "currency",
+                  "x",
+                  "%",
+                  "months"
+                ],
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "value": {
+            "type": [
+              "number",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "label",
+          "value",
+          "unit",
+          "display"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "notes": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "title": {
+      "type": "string"
+    },
+    "tool": {
+      "description": "The calculator tool that produced this result",
+      "type": "string"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "kind",
+    "tool",
+    "title",
+    "calculator",
+    "url",
+    "bookingUrl",
+    "currency",
+    "compact",
+    "inputs",
+    "metrics",
+    "notes",
+    "benchmarks"
+  ],
+  "type": "object"
+}

First observedSep 29, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare a pure read-only, idempotent, non-destructive, closed-world computation, so the safety profile is fully covered. The description adds the exact statistical method (two-proportion z-test), which is genuinely useful behavioral context, but says nothing about edge cases such as zero visitors or low sample sizes.

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 purpose in one tight sentence; the follow-on link is short but is promotional rather than agent-relevant, so it does not fully earn its place.

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?

For a stateless calculator with complete annotations, a 100%-covered schema, and an output schema that covers return values, the description is sufficient. Only minor behavioral caveats (input validity or sample-size assumptions) are absent.

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% with clear per-parameter descriptions, so the schema carries the parameter burden. The description adds no extra meaning about the required counts or the optional currency field, making the baseline 3 correct.

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?

States a specific verb (Run) and resource (two-proportion z-test on an A/B test) and names the outputs (relative uplift, statistical confidence), so the agent knows exactly what computation this performs. No sibling tool duplicates an A/B significance test, so it is unambiguous.

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 usage scenario is implied: this applies when you have A/B visitors/conversions and want significance. However, the description gives no explicit when-to-use, when-not-to-use, or alternative referral guidance.

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

All Rahul D Sarker: Marketing & RevOps Tools tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?