MartinLoop — Stop Runaway Loops, Bad Code & Token Waste

martin_cancel

Destructive

Cancel a MartinLoop run by file, loop ID, or latest run, and write a durable cancellation receipt. Abandon work permanently with optional reason and requester for audit.

Instructions

Write a durable cancellation receipt for one canonical MartinLoop run. Provide exactly one selector: file, loopId, or latest; runsDir changes the run-store root, while reason and requestedBy add audit context. Use when work must be abandoned, not temporarily held. This records a request and does not kill a process; use martin_pause for a reversible hold.

Input Schema

TableJSON Schema

Name	Required	Description
`file`	No	Path to one canonical run record or directory. Mutually exclusive with loopId and latest.
`latest`	No	When true, targets the latest canonical run. Mutually exclusive with file and loopId.
`loopId`	No	Canonical MartinLoop run identifier. Mutually exclusive with file and latest.
`reason`	No	Optional non-empty reason recorded in the cancellation receipt.
`runsDir`	No	Optional run-store root override used to resolve loopId or latest.
`requestedBy`	No	Optional human or runtime identity label recorded for audit context.

Output Schema

TableJSON Schema

Name	Required	Description
`action`	Yes	The control action that was recorded.
`loopId`	Yes	MartinLoop run identifier the control was applied to.
`reason`	No	Human-readable reason for the control, if provided.
`controlId`	Yes	Unique receipt ID for this control action.
`requestedAt`	Yes	ISO 8601 timestamp when the control was recorded.
`requestedBy`	No	Identity that requested the control, if provided.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.5.9Sep 2, 2026

addedInput schema / properties / file / description

Added value: +"Path to one canonical run record or directory. Mutually exclusive with loopId and latest."

addedInput schema / properties / latest / description

Added value: +"When true, targets the latest canonical run. Mutually exclusive with file and loopId."

addedInput schema / properties / loopId / description

Added value: +"Canonical MartinLoop run identifier. Mutually exclusive with file and latest."

addedInput schema / properties / reason / description

Added value: +"Optional non-empty reason recorded in the cancellation receipt."

addedInput schema / properties / requestedBy / description

Added value: +"Optional human or runtime identity label recorded for audit context."

addedInput schema / properties / runsDir / description

Added value: +"Optional run-store root override used to resolve loopId or latest."

Changed3 schema fields changedv0.5.6Aug 30, 2026

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

addedOutput schema / properties

Added value: +{
+  "action": {
+    "description": "The control action that was recorded.",
+    "enum": [
+      "pause",
+      "cancel",
+      "continue"
+    ],
+    "type": "string"
+  },
+  "controlId": {
+    "description": "Unique receipt ID for this control action.",
+    "type": "string"
+  },
+  "loopId": {
+    "description": "MartinLoop run identifier the control was applied to.",
+    "type": "string"
+  },
+  "reason": {
+    "description": "Human-readable reason for the control, if provided.",
+    "type": "string"
+  },
+  "requestedAt": {
+    "description": "ISO 8601 timestamp when the control was recorded.",
+    "type": "string"
+  },
+  "requestedBy": {
+    "description": "Identity that requested the control, if provided.",
+    "type": "string"
+  }
+}

addedOutput schema / required

Added value: +[
+  "loopId",
+  "action",
+  "controlId",
+  "requestedAt"
+]

First observedv0.3.9Jul 29, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already mark destructiveHint=true and idempotentHint=false. The description adds behavioral nuance beyond that by clarifying that the tool 'records a request and does not kill a process' and that the receipt is 'durable.' It does not fully spell out what state changes the cancellation causes, but it meaningfully reduces ambiguity around process termination.

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?

Three sentences, all front-loaded and purposeful. The core action and primary constraint come first, followed by usage conditions and the key alternative. No filler or repetition of schema details.

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 output schema exists, return values need not be described. The description covers when to use it, when not to, how selectors work, the side-effect boundary, and the audit parameters. Nothing essential is missing for an agent to select and invoke the tool correctly.

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%, so the baseline is 3. The description adds value by grouping parameters semantically: it states the exact-one-selector requirement among file, loopId, and latest, explains runsDir as a run-store root override, and identifies reason and requestedBy as audit context. This goes beyond the schema's per-property text.

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 opens with a specific verb-resource pair: 'Write a durable cancellation receipt for one canonical MartinLoop run.' It clearly defines scope ('one... run') and differentiates the tool by noting it records a request rather than killing a process, which separates it from siblings like martin_pause.

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?

Explicit usage guidance is provided: 'Use when work must be abandoned, not temporarily held' and 'use martin_pause for a reversible hold.' This gives an agent a clear decision rule and names the alternative tool for the opposite case.

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