Skip to main content
Glama

丢弃影子副本

app_discard_shadow

Discard a shadow copy and its unapplied changes without modifying the original directory. Use it to clean up isolated edits you choose not to apply.

Instructions

UI 专用:删除影子副本及其未应用的改动,不触碰原目录。

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": {
      "shadowId": "<shadowId>"
    },
    "name": "app_discard_shadow"
  }
}

Input Schema

NameRequiredDescriptionDefault
shadowIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden, and it does disclose the crucial blast radius: the shadow copy and its unapplied changes are destroyed while the original directory survives. It omits reversibility, whether the operation requires a live session, and what happens if changes were already applied.

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?

One short sentence, front-loaded with the UI-only qualifier and then the destructive scope, with no filler. Nothing is repeated for padding, though the Chinese-language constraint prefix is terse enough that an agent could read past it.

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

Completeness3/5

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

For a single-parameter destructive tool with no annotations and no output schema, the description covers the destructive scope well but leaves the input and the return behavior unexplained. An agent could call it, but not confidently identify the correct shadowId.

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?

There is one required parameter, shadowId, at 0% schema description coverage, so the schema adds nothing beyond its type. The description does not explain what identifier this is or where an agent obtains it, leaving the only input effectively undocumented.

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?

The description names a specific verb+resource pair ('deletes the shadow copy and its unapplied changes') and scopes it negatively ('does not touch the original directory'), which separates it from app_apply_shadow by implication. It stops short of naming that sibling explicitly, so an agent must infer the pairing rather than being told.

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?

'UI 专用' (UI-only) is a real usage constraint, but it constrains the caller channel rather than the situation. There is no statement of when to discard versus apply or abort an in-flight job, and no mention of preconditions such as whether unapplied changes must exist.

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