Skip to main content
Glama
huaidj-rufus

huaidj-rufus

by huaidj

execute_disk_operation

Destructive

Execute a prepared USB format or repartition plan after explicit user authorization. Rechecks disk identity and partition bounds before writing, and refuses active system or internal disks.

Instructions

DESTRUCTIVE: execute the exact prepared USB format/repartition plan after explicit user authorization. Rechecks physical identity and partition bounds. Active system/internal disks remain refused.

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": "execute_disk_operation"
  }
}

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

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the 'DESTRUCTIVE' prefix largely restates structured data. The description earns credit for genuinely new behavior: it rechecks physical disk identity and partition bounds at execution time, and it refuses active system/internal disks even if authorized - safety guarantees an agent cannot read from annotations alone.

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?

Three short sentences, hazard flagged first, preconditions second, safety guarantees third. No filler and nothing important buried mid-paragraph.

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 destructive, non-idempotent operation the coverage of the safety/authorization story is good, but the mechanics of the mandatory 'confirmation' argument and what happens after invocation (is progress observed via disk_job_status or usb_write_status? is a partially completed format recoverable?) are left unstated.

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 coverage is only 33% and the description adds nothing about the parameters. plan_id is self-documenting via the schema's reference to prepare_usb_write, and confirm_erase is a const true, but the required 'confirmation' string is unexplained in both places - an agent cannot tell whether it is a typed phrase, a user-supplied token, or an echo of the plan ID.

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 uses a specific verb plus resource - 'execute the exact prepared USB format/repartition plan' - and scopes it against the family of preparation and dry-run siblings by insisting on a *prepared* plan. An agent can tell immediately this is the commit step, not the planning or status 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?

It states the precondition clearly: a plan must already exist and explicit user authorization must have been obtained. It does not, however, name or exclude alternatives such as dry_run_usb_plan or write_usb, so the agent must infer that this is the post-plan commit path rather than the direct-write path.

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