Skip to main content
Glama
huaidj-rufus

huaidj-rufus

by huaidj

prepare_disk_operation

Creates an expiring, exact-target plan to format one USB partition or erase and reinitialize a whole USB, reporting scope before any destructive action without writing to the target.

Instructions

Prepare an expiring exact-target plan to format one USB partition or erase/reinitialize the whole USB. Reports the scope before any destructive action; does not write the target.

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": {
      "operation": "<operation>",
      "device_number": "<device_number>",
      "filesystem": "<filesystem>"
    },
    "name": "prepare_disk_operation"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelNo
quickNo
operationYes
filesystemYes
device_numberYes
partition_styleNoGPT
partition_numberNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

The annotations already declare that this is not a read-only operation and that destructiveHint=false; the description reconciles both by saying it does not write the target. It adds behavior that the annotations do not capture: the plan is 'expiring', the target must be 'exact', and the scope is reported before action. It omits the expiry duration and whether a consumed or expired plan errors out, which keeps it below a 5.

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?

Two dense sentences with zero filler: the first sentence states what the tool produces and the two scopes, and the second sentence front-loads the safety guarantee. Nothing is repeated from the schema or annotations.

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 seven-parameter planning tool with no output schema and no schema descriptions, the definition should describe the plan's contents and validity window, and clarify how the required parameters interact. It covers the conceptual model well but leaves too much unspecified for an agent to fill in the schema correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden of explaining the parameters. It does map the operation modes to partition-level versus whole-device targeting, but it says nothing about label, quick, filesystem, partition_style, or the required pairing between operation and partition_number, so four of the seven parameters remain undefined anywhere.

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 uses a specific verb and resource: it 'prepares' an 'expiring exact-target plan' that targets 'one USB partition' or 'the whole USB'. The clause 'does not write the target' clearly separates this tool from the execution sibling, but it never names that sibling, so the contrast must be inferred.

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?

The phrase 'Reports the scope before any destructive action' implies this is the pre-flight step for something destructive, which is useful context. However, it never says explicitly 'call this before execute_disk_operation' or states any condition, such as when not to use it or when an existing plan is still valid.

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