patchwork-os

refactorPreview

Preview refactoring edits across files without applying. Retrieve code actions first, then review changes before committing.

Instructions

Preview refactoring edits across files without applying. Use getCodeActions first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "filePath": "<filePath>",
      "startLine": "<startLine>",
      "startColumn": "<startColumn>",
      "endLine": "<endLine>",
      "endColumn": "<endColumn>",
      "actionTitle": "<actionTitle>"
    },
    "name": "refactorPreview"
  }
}

Input Schema

Name	Required	Description
`endLine`	Yes	End line (1-based)
`filePath`	Yes	Workspace or absolute path
`endColumn`	Yes	End column (1-based)
`startLine`	Yes	Start line (1-based)
`actionTitle`	Yes	Exact action title from getCodeActions output
`startColumn`	Yes	Start column (1-based)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0May 20, 2026

TDQS

A3.8/5.0

Behavior3/5

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It correctly communicates that the tool does not apply edits (non-destructive). However, it does not describe the output format (e.g., diff, list of changes) or any side effects, leaving the agent with partial understanding of the tool's behavior.

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 two sentences, no wasted words, and efficiently conveys the core purpose and a critical prerequisite. It is well-structured and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having 6 parameters and no output schema, the description does not explain what the preview output looks like (e.g., inline diff, list of file changes) or provide example usage. For a multi-file refactoring preview tool, this leaves the agent with incomplete context to anticipate results.

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 covers 100% of parameters with clear descriptions (filePath, line/col ranges, actionTitle). The tool description adds no extra parameter-level detail beyond the schema, which is acceptable given the 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 clearly states it 'Preview refactoring edits across files without applying', providing a specific verb (preview) and resource (refactoring edits). It distinguishes itself from siblings like applyCodeAction (which applies) and getCodeActions (which retrieves actions) by emphasizing the non-applying aspect and the prerequisite step.

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

Usage Guidelines4/5

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

The description explicitly instructs to 'Use getCodeActions first', establishing a clear prerequisite for the tool's workflow. It implies the tool is for previewing before applying, though it does not explicitly state when not to use it or provide alternatives beyond the implied sequence.

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

Deploy Server