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

run_pr_gate_pipeline

Read-onlyIdempotent

Review triage for a pull request. Takes a unified git diff (git diff HEAD) and returns: diff-lint findings with the lines that produced them, regression impact areas, a risk score 0–100 with the factors that built it (churn, files touched, sensitive paths, whether any test file changed, lint severities, impacted risk areas), generated test cases, and a PASS / CONDITIONAL / BLOCK recommendation. Advisory: the score measures properties of the diff, not the correctness of the change — it does not read the code semantically and does not replace a reviewer or a static analyser. See notAnalysed in the response.

Input Schema

Name	Required	Description	Default
`context`	No	Optional PR title or description for richer analysis
`git_diff`	Yes	Unified git diff (output of `git diff HEAD` or copied from GitHub diff view)

Output Schema

Name	Required	Description	Default
`sla`	No
`high`	No
`topBugs`	No
`critical`	No
`bugsFound`	No
`riskLevel`	No
`riskScore`	No
`disclaimer`	No
`impactAreas`	No
`inputFormat`	No
`notAnalysed`	No
`riskFactors`	No
`changedFiles`	No
`severityLevel`	No
`testCasesGenerated`	No
`mergeRecommendation`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

addedInput schema / examples

Added value: +[
+  {
+    "git_diff": "diff --git a/pay.js b/pay.js\n--- a/pay.js\n+++ b/pay.js\n@@ -1 +1 @@\n-if (amount > 0) charge(amount);\n+if (amount >= 0) charge(amount);"
+  }
+]

Changed4 schema fields changedJul 29, 2026
- addedOutput schema / properties / disclaimer
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / inputFormat
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / notAnalysed
```
Added value: +{
+  "type": "array"
+}
```
- addedOutput schema / properties / riskFactors
```
Added value: +{
+  "type": "array"
+}
```

Changed1 schema field changedJun 21, 2026

addedOutput schema / properties

Added value: +{
+  "bugsFound": {
+    "type": "number"
+  },
+  "changedFiles": {},
+  "critical": {},
+  "high": {},
+  "impactAreas": {
+    "type": "array"
+  },
+  "mergeRecommendation": {},
+  "riskLevel": {},
+  "riskScore": {},
+  "severityLevel": {},
+  "sla": {},
+  "testCasesGenerated": {},
+  "topBugs": {
+    "type": "array"
+  }
+}

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

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

First observedMay 26, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, and the description still adds substantive context: exactly which factors build the risk score (churn, files touched, sensitive paths, test-file changes, lint severities, impacted risk areas) and an explicit limitation that it does not read code semantically. It also redirects the reader to the notAnalysed field for unanalysed areas — genuinely beyond what the annotations say.

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 purpose, then the return set, then the caveat. The return enumeration is long but each item earns its place for tool selection; the one weak spot is that the output set is repeated almost verbatim against the output schema while the more decision-relevant caveat sits at the end.

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 read-only analysis pipeline with a full output schema, the description covers input contract, output shape, decision semantics and known limitations. Missing only practical edges such as behaviour on malformed/large diffs or minimum diff size for meaningful output.

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 coverage is 100% and both parameters are documented there, so the schema does the heavy lifting. The description reinforces the required input's format (`git diff HEAD`) but adds nothing about the optional `context` parameter or about diff size/format failure modes, so the baseline 3 applies.

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?

Specific verb+resource ('Review triage for a pull request') followed by an exhaustive enumeration of the artifacts returned: diff-lint findings, regression areas, risk score, generated tests, and a PASS/CONDITIONAL/BLOCK recommendation. It does not, however, distinguish itself from the sibling pr_gatekeeper or analyze_diff_bugs, which is the only real gap.

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?

It states the input contract (`git diff HEAD`) and a clear advisory boundary — the score measures diff properties, not correctness, and does not replace a reviewer or static analyser. That is a useful when-not signal, but no alternative tool is named and no positive triggering condition (e.g. 'use before opening a PR') is given.

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.