Skip to main content
Glama
huaidj-rufus

huaidj-rufus

by huaidj

write_usb

Destructive

Overwrites every partition on a specified USB drive using a confirmed, unexpired plan and the Rufus engine while rejecting internal disks. Requires explicit authorization and returns a job ID to poll for write status.

Instructions

DESTRUCTIVE: overwrite every partition and file on the physical USB named by an unexpired plan, using the real Rufus native engine. Requires explicit user authorization and the exact plan confirmation. Revalidates device identity and image hash; refuses internal/system disks. Returns a job ID, not write completion. Poll usb_write_status.

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": {
      "plan_id": "<plan_id>",
      "confirmation": "<confirmation>",
      "confirm_erase": "<confirm_erase>"
    },
    "name": "write_usb"
  }
}

Input Schema

NameRequiredDescriptionDefault
plan_idYesThe unexpired plan ID returned by prepare_usb_write.
confirmationYes
confirm_eraseYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds materially more: the full extent of destruction (every partition and file), required user authorization, identity and image-hash revalidation at execution time, refusal of internal/system disks, and the crucial fact that it returns a job ID rather than write completion. That async contract is not encoded anywhere in the annotations or schema.

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?

Four sentences, front-loaded with the DESTRUCTIVE warning, then preconditions, then runtime safeguards, then the async return contract. Every clause conveys operationally relevant information with no filler.

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

Completeness4/5

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

For a destructive, non-idempotent, async write with no output schema, the definition covers safety gates, validation, refusal conditions, and the polling handoff. The only gap is the undocumented confirm_erase parameter, which the agent must discover from the schema.

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?

With only 33% schema coverage, the description must carry parameter meaning. It does explain plan_id (unexpired plan from prepare_usb_write) and gestures at confirmation ('the exact plan confirmation'), but the confirm_erase boolean is never mentioned beyond the general DESTRUCTIVE framing, so an agent must read the schema to learn it is a const-true acknowledgement flag.

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 opens with a specific verb and resource ('overwrite every partition and file on the physical USB'), scopes it to a plan produced by prepare_usb_write, and names the Rufus native engine. An agent can distinguish this write tool from prepare_usb_write and dry_run_usb_plan without opening any schema.

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?

It states the preconditions for use (an unexpired plan, explicit user authorization, exact plan confirmation) and the follow-up step (poll usb_write_status), plus a hard exclusion: internal/system disks are refused. It stops short of explicitly telling the agent to run dry_run_usb_plan or prepare_usb_write first, leaving that ordering to inference from the plan_id dependency.

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