Mushi-Mushi

Fix context bundle

get_fix_context

Read-onlyIdempotent

Retrieve a complete bug-fix package: plain-English diagnosis, reproduction steps, root cause, and a paste-ready fix prompt for any report.

Instructions

Bundle everything an agent needs to fix one bug in a single call: a paste-ready fixPrompt (plain-English diagnosis + reproduction + suggested fix + relevant code + blast radius), plus report detail, repro steps, component, root cause, ontology tags, and the inventory action (with its expected_outcome contract) the report is filed against. Returns { report, fixPrompt, reproductionSteps, component, rootCause, bugOntologyTags, inventoryAction }. Read-only; no second LLM key needed. Use before writing a fix; use triage_issue for a multi-report review packet, or suggest_fix for just the Stage-2 hint.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`reportId`	Yes	The report UUID to fix (`report_id` is accepted too.)
`projectId`	No	Project UUID — required for org-scoped keys with multiple projects. (`project_id` is accepted too.)

Output Schema

TableJSON Schema

Name	Required	Description
`report`	Yes
`component`	Yes	Component or page the bug was attributed to
`fixPrompt`	Yes	Paste-ready fix prompt composed server-side, or null
`rootCause`	Yes	Stage-2 root cause, or null before Stage 2 runs
`bugOntologyTags`	Yes	Bug ontology tags, or null
`inventoryAction`	Yes	The inventory action (with its expected_outcome contract) the report is filed against, or null
`reproductionSteps`	Yes	Reproduction steps recorded on the report ([] if none)

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedv0.1.12Sep 24, 2026

addedInput schema / properties / projectId

Added value: +{
+  "description": "Project UUID — required for org-scoped keys with multiple projects. (`project_id` is accepted too.)",
+  "type": "string"
+}

removedInput schema / properties / project_id

Removed value: -{
-  "description": "Project UUID — required for org-scoped keys with multiple projects.",
-  "type": "string"
-}

changedInput schema / properties / reportId / description

Previous value: -"The report UUID to fix"New value: +"The report UUID to fix (`report_id` is accepted too.)"

addedOutput schema / properties / bugOntologyTags / description
```
Added value: +"Bug ontology tags, or null"
```

addedOutput schema / properties / component / description

Added value: +"Component or page the bug was attributed to"

addedOutput schema / properties / component / type
```
Added value: +[
+  "string",
+  "null"
+]
```

addedOutput schema / properties / fixPrompt / description

Added value: +"Paste-ready fix prompt composed server-side, or null"

addedOutput schema / properties / inventoryAction

Added value: +{
+  "description": "The inventory action (with its expected_outcome contract) the report is filed against, or null"
+}

addedOutput schema / properties / report / additionalProperties
```
Added value: +{}
```

addedOutput schema / properties / report / properties

Added value: +{
+  "breadcrumbs": {},
+  "category": {
+    "description": "bug | slow | visual | confusing | other",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "child_report_ids": {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "component": {
+    "description": "Component or page the bug was attributed to",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "console_logs": {
+    "description": "Console entries captured with the report"
+  },
+  "created_at": {
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "description": {
+    "description": "What the reporter wrote (untrusted text)",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "environment": {
+    "description": "Browser/OS/viewport the SDK captured"
+  },
+  "fix_attempts": {
+    "description": "Latest fix attempts, newest first",
+    "items": {
+      "additionalProperties": {},
+      "properties": {
+        "id": {
+          "type": "string"
+        },
+        "status": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "id"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "fix_packet": {
+    "description": "Paste-ready fix prompt composed server-side"
+  },
+  "id": {
+    "description": "Report UUID",
+    "type": "string"
+  },
+  "inventory_action": {
+    "description": "Inventory action the report is filed against, when resolved"
+  },
+  "network_logs": {
+    "description": "Network requests captured with the report"
+  },
+  "project_id": {
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "reproduction_steps": {},
+  "screenshot_url": {
+    "description": "Signed screenshot URL",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "severity": {
+    "description": "critical | high | medium | low",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "stage1_classification": {
+    "description": "Stage-1 (fast) classification"
+  },
+  "stage2_analysis": {
+    "description": "Stage-2 analysis: rootCause, suggestedFix, …"
+  },
+  "status": {
+    "description": "Workflow status, e.g. new, classified, fixing, fixed, verified, reopened",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "summary": {
+    "description": "One-line summary written by the classifier",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "title": {
+    "type": [
+      "string",
+      "null"
+    ]
+  }
+}

addedOutput schema / properties / report / required
```
Added value: +[
+  "id"
+]
```
addedOutput schema / properties / report / type
```
Added value: +"object"
```

addedOutput schema / properties / reproductionSteps / description

Added value: +"Reproduction steps recorded on the report ([] if none)"

addedOutput schema / properties / rootCause / description

Added value: +"Stage-2 root cause, or null before Stage 2 runs"

changedOutput schema / required

Previous value: -[
-  "report",
-  "fixPrompt",
-  "reproductionSteps",
-  "component",
-  "rootCause",
-  "bugOntologyTags"
-]New value: +[
+  "report",
+  "fixPrompt",
+  "reproductionSteps",
+  "component",
+  "rootCause",
+  "bugOntologyTags",
+  "inventoryAction"
+]

Changed2 schema fields changedv0.1.10Sep 15, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

First observedv0.1.0Jun 24, 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, openWorldHint, and idempotentHint. The description adds valuable context beyond those: it is read-only, requires 'no second LLM key needed,' and explains that the fixPrompt is 'paste-ready' with a specific composition (diagnosis, reproduction, suggested fix, relevant code, blast radius). This goes beyond the annotations and schema by clarifying operational and content expectations.

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 information-dense but every sentence earns its place: purpose, bundled contents, return shape, read-only/cost note, and usage routing. It is front-loaded with the core purpose and does not waste words on redundancy or fluff.

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?

The tool has an output schema, so the description does not need to explain return values in detail. It covers when to use the tool, what it returns conceptually, its read-only nature, the absence of a second LLM key requirement, and how to route to alternatives. For a read-only bundle tool with clear annotations, this description is complete enough for correct invocation.

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 both reportId and projectId already described in the input schema. The description does not add substantial parameter-specific semantics beyond what the schema provides; it mentions report detail and project context only implicitly. With full schema coverage, the baseline of 3 is appropriate.

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 action ('Bundle everything an agent needs to fix one bug in a single call') and enumerates the bundled contents, the exact return fields, and the tool's relationship to siblings. It distinguishes itself from triage_issue and suggest_fix by naming what each alternative is for, so an agent can select the right tool without opening schemas.

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 gives explicit guidance: 'Use before writing a fix' and then names concrete alternatives with their specific scopes ('use triage_issue for a multi-report review packet, or suggest_fix for just the Stage-2 hint'). This directly tells the agent when to use this tool versus its closest siblings, leaving no ambiguity.

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