MartinLoop — Stop Runaway Loops, Bad Code & Token Waste

martin_review_pr

Read-onlyIdempotent

Review a pull request body against the MartinLoop run dossier and evidence, returning a verdict with specific findings. Ensure the PR accurately reflects governed run data before merging.

Instructions

Review a PR body or draft against the MartinLoop run dossier and evaluation evidence, and return a verdict with specific findings. Use when you have an existing PR body and want to check whether it accurately represents the governed run evidence. Supply prBody to review a specific body string; omit it to evaluate the auto-generated dossier body. Do not use to generate a PR body from scratch — use martin_pr_summary instead. Do not use to open or create a PR — use martin_create_pr instead. This tool only reads saved run evidence and does not modify the repository or contact GitHub.

Input Schema

TableJSON Schema

Name	Required	Description
`file`	No	Absolute or relative path to a loop-record.json file or run directory. Mutually exclusive with loopId and latest.
`format`	No	Dossier format used when generating the reference body for comparison. Defaults to github-pr.
`latest`	No	When true, reviews against the most recently updated run. Mutually exclusive with file and loopId.
`loopId`	No	MartinLoop run identifier from the run store. Mutually exclusive with file and latest.
`prBody`	No	The PR body text to review. If omitted, the auto-generated dossier body is evaluated instead.
`runsDir`	No	Override the default run-store root directory. Optional.

Output Schema

TableJSON Schema

Name	Required	Description
`loopId`	Yes	MartinLoop run identifier the review was performed against.
`summary`	Yes	Plain-English review summary.
`verdict`	Yes	Merge verdict: approve_with_review means safe to merge with human review; needs_changes requires fixes; blocked means do not merge.
`findings`	Yes	Specific findings that informed the verdict.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.6.6Sep 23, 2026

removedInput schema / oneOf

Removed value: -[
-  {
-    "required": [
-      "file"
-    ]
-  },
-  {
-    "required": [
-      "loopId"
-    ]
-  },
-  {
-    "required": [
-      "latest"
-    ]
-  }
-]

Changed9 schema fields changedv0.5.6Aug 30, 2026

addedInput schema / properties / file / description

Added value: +"Absolute or relative path to a loop-record.json file or run directory. Mutually exclusive with loopId and latest."

addedInput schema / properties / format / description

Added value: +"Dossier format used when generating the reference body for comparison. Defaults to github-pr."

addedInput schema / properties / latest / description

Added value: +"When true, reviews against the most recently updated run. Mutually exclusive with file and loopId."

addedInput schema / properties / loopId / description

Added value: +"MartinLoop run identifier from the run store. Mutually exclusive with file and latest."

addedInput schema / properties / prBody / description

Added value: +"The PR body text to review. If omitted, the auto-generated dossier body is evaluated instead."

addedInput schema / properties / runsDir / description

Added value: +"Override the default run-store root directory. Optional."

changedOutput schema / additionalProperties
```
Previous value: -trueNew value: +false
```

addedOutput schema / properties

Added value: +{
+  "findings": {
+    "description": "Specific findings that informed the verdict.",
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "loopId": {
+    "description": "MartinLoop run identifier the review was performed against.",
+    "type": "string"
+  },
+  "summary": {
+    "description": "Plain-English review summary.",
+    "type": "string"
+  },
+  "verdict": {
+    "description": "Merge verdict: approve_with_review means safe to merge with human review; needs_changes requires fixes; blocked means do not merge.",
+    "enum": [
+      "approve_with_review",
+      "needs_changes",
+      "blocked"
+    ],
+    "type": "string"
+  }
+}

addedOutput schema / required

Added value: +[
+  "loopId",
+  "verdict",
+  "findings",
+  "summary"
+]

First observedv0.3.9Jul 29, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is well-covered. The description adds valuable context beyond annotations: it clarifies the tool 'only reads saved run evidence and does not modify the repository or contact GitHub,' which is a specific behavioral guarantee not present in the annotations. It also explains the behavior of omitting prBody (evaluates the auto-generated body). This adds meaningful behavioral transparency without contradicting any annotations.

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 front-loaded with the core purpose, then provides usage guidance, exclusions, and a safety note in a logical flow. Every sentence serves a distinct function—purpose, when-to-use, exclusions, and behavioral transparency—with no filler or redundancy. It is appropriately sized for the tool's complexity.

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 tool has an output schema and rich annotations, the description covers all essential aspects: it explains what the tool does, when to use it, when not to use it (with alternatives), the key parameter behavior (prBody omission), and its non-destructive nature. No critical information is missing for an agent to select and invoke this 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 has 100% description coverage, so each parameter's purpose is already well-documented. The description adds minimal additional parameter semantics: it reiterates the prBody behavior (supply to review a specific body; omit to evaluate the auto-generated one) which duplicates the schema's description. No other parameters receive additional explanation in the description, so it does not exceed the baseline expected for high schema coverage.

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 states a specific verb ('Review'), a specific resource ('PR body or draft against the MartinLoop run dossier and evaluation evidence'), and a specific output ('a verdict with specific findings'). It also differentiates itself from siblings by naming martin_pr_summary and martin_create_pr as alternatives for different tasks, making the tool's distinct role unambiguous.

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

Usage Guidelines5/5

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

The description explicitly states when to use this tool ('Use when you have an existing PR body and want to check whether it accurately represents the governed run evidence') and when not to use it, naming the exact alternative tools ('Do not use to generate a PR body from scratch — use martin_pr_summary instead. Do not use to open or create a PR — use martin_create_pr instead.'). This provides clear routing with no ambiguity.

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