IA-QA — 152 QA & Dev Tools for AI Agents

ab_test_report

Read-onlyIdempotent

Generate an A/B test report comparing two prompts or model configurations. Accepts arrays of scores and returns mean, median, std deviation, improvement percentage, and a Welch t-test at 95 %: winner names a variant only when the difference is significant — otherwise "no_significant_difference", or "insufficient_samples" under 2 scores per variant.

Input Schema

Name	Required	Description	Default
`variant_a`	Yes	First variant configuration with name and score array
`variant_b`	Yes	Second variant configuration with name and score array

Output Schema

Name	Required	Description	Default
`max`	No
`min`	No
`mean`	No
`count`	No
`median`	No
`winner`	No
`std_dev`	No
`variant_a`	No
`variant_b`	No
`recommendation`	No
`improvement_percent`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

addedInput schema / examples

Added value: +[
+  {
+    "variant_a": {
+      "name": "A",
+      "scores": [
+        70,
+        71,
+        69
+      ]
+    },
+    "variant_b": {
+      "name": "B",
+      "scores": [
+        70,
+        71,
+        69
+      ]
+    }
+  }
+]

Changed1 schema field changedJun 21, 2026

addedOutput schema / properties

Added value: +{
+  "count": {
+    "type": "number"
+  },
+  "improvement_percent": {},
+  "max": {},
+  "mean": {
+    "type": "string"
+  },
+  "median": {
+    "type": "string"
+  },
+  "min": {},
+  "recommendation": {
+    "type": "number"
+  },
+  "std_dev": {
+    "type": "string"
+  },
+  "variant_a": {
+    "type": "object"
+  },
+  "variant_b": {
+    "type": "object"
+  },
+  "winner": {}
+}

Changed2 schema fields changedJun 11, 2026
- addedInput schema / properties / variant_a / description
```
Added value: +"First variant configuration with name and score array"
```
- addedInput schema / properties / variant_b / description
```
Added value: +"Second variant configuration with name and score array"
```

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

First observedMay 26, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds real behavioral detail beyond that — the significance test used (Welch t-test at 95%), the rule that `winner` is only named when significant, and the fallback states "no_significant_difference" and "insufficient_samples". This is meaningful outcome-condition disclosure that the annotations cannot express.

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?

Two compact sentences: the first states purpose, the second delivers output list and decision rules. Nothing is redundant and the most decision-relevant detail (the winner/significance logic) 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 enumerating return fields is arguably redundant, but the description adds value by explaining the conditional semantics behind `winner`. Combined with the minimum-sample rule and the statistical method, it covers what an agent needs; only the absence of guidance on sample-size adequacy or non-normal data keeps it from a 5.

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% and both nested params are documented, so the baseline is 3. The description adds a constraint the schema omits: at least 2 scores per variant are required, otherwise "insufficient_samples" is returned. That is a genuine semantic addition beyond the structured fields.

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 opens with a specific verb+resource ("Generate an A/B test report") and scopes it to comparing two prompts or model configurations via score arrays, which separates it from generic comparators like compare_responses. It stops short of naming a sibling alternative explicitly, so it is clear but not maximally differentiating.

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: you supply two score arrays and get a comparison. There is no explicit statement of when to use this over compare_models or compare_responses, nor any exclusion of pre-computed metrics versus raw prompts. An agent must infer the context from the description.

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

All IA-QA — 152 QA & Dev Tools for AI Agents 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.