Skip to main content
Glama
MD MCP Plugin

MD MCP Plugin

by yanling37

md_recover_cut_operation

Reloads the saved project to recover a completed Cut with partial verification, discarding unsaved changes only when batch, readback, and source SHA match the original receipt.

Instructions

Reload the same saved project after a completed Cut with partial verification.

This discards the project's unsaved changes. The input batch, current readback and saved source SHA must match the original receipt. The original result is retained.

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": {
      "blocked_request_id": "<blocked_request_id>",
      "request_id": "<request_id>",
      "scene_token": "<scene_token>",
      "expected_source_sha256": "<expected_source_sha256>"
    },
    "name": "md_recover_cut_operation"
  }
}

Input Schema

NameRequiredDescriptionDefault
request_idYes
scene_tokenYes
blocked_request_idYes
expected_source_sha256Yes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it explicitly warns that unsaved project changes are discarded, defines the three-way verification precondition, and notes that the original result is retained so the agent knows recovery is non-destructive to prior output. It still omits what happens on a verification mismatch (error vs. partial state) and whether concurrent access is an issue.

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?

Four short lines, with the action first and the destructive consequence immediately after, so the riskiest information is front-loaded. Minor redundancy between the title-like first sentence and the rest, but nothing is padding.

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 four-required-parameter, no-annotation, no-output-schema recovery tool, the description covers the destructive side effect, preconditions and result retention well. It leaves the return value, failure behavior and the ordering relative to status/inspection siblings unaddressed, which matters for a recovery operation an agent might call defensively.

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 0% and all four parameters are required title-only strings. The description partially compensates by mapping 'input batch', 'current readback' and 'saved source SHA' onto request/blocked-request, scene token and expected_source_sha256, but the mapping is implicit and neither 'blocked_request_id' nor 'scene_token' is explained in a way an agent could act on without guessing.

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 gives a specific verb+resource ('Reload the same saved project') and scopes it to 'a completed Cut with partial verification', which is concrete enough to distinguish it from lookup-type siblings such as md_operation_status or cut_inspect. It does not explicitly name a near-twin like md_recover_curve_operation, but the domain qualifier ('Cut') does most of that work.

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?

It states the triggering situation ('after a completed Cut with partial verification') and the precondition that the batch, readback and saved source SHA must match the original receipt. It gives no when-not guidance, no mention of what to do if verification fails, and no pointer to an alternative like md_operation_status for checking state first.

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

Deploy Server

Other Tools