Skip to main content
Glama

flipper_badusb_create

DestructiveIdempotent

Write a BadUSB DuckyScript file to a Flipper Zero for authorized testing of your own PC; adds .txt if missing and saves without executing it.

Instructions

Write a BadUSB DuckyScript to /ext/badusb/ on the Flipper, for testing a PC you own. The agent authors the DuckyScript (DELAY, STRING, ENTER, GUI r, CTRL ALT DEL, etc.). Adds a .txt extension if missing. Does not run it.

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": {
      "filename": "<filename>",
      "ducky_script": "<ducky_script>"
    },
    "name": "flipper_badusb_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
filenameYes
ducky_scriptYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true, and openWorldHint=false, so the safety profile is covered; the description adds that the file lands under /ext/badusb/ and that a .txt extension is appended automatically. The notable omission is overwrite behavior — destructiveHint=true implies an existing same-named file is replaced, but the description never says so, nor whether the target directory is created.

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 tight sentences, front-loaded with verb, format, and destination path, followed by the parameter detail and the non-execution caveat. The DuckyScript keyword examples are compact and directly useful rather than 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?

An output schema exists, so return values need no explanation, and the description covers the essentials for a two-parameter write: destination path, extension handling, and that nothing executes. The remaining hole is collision/overwrite semantics for a tool annotated as destructive.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must carry both parameters, and it does: filename gains the /ext/badusb/ prefix and the automatic .txt append rule, while ducky_script is clarified as agent-authored DuckyScript with example commands (DELAY, STRING, ENTER, GUI r, CTRL ALT DEL). It does not specify filename constraints such as allowed characters or length, leaving a minor gap against the zero-coverage schema.

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?

States a specific verb and resource with the exact destination path: "Write a BadUSB DuckyScript to /ext/badusb/<filename> on the Flipper." It also explicitly distinguishes itself from the execution sibling with "Does not run it," so an agent can separate it from flipper_badusb_run without opening either 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?

Gives a clear use context ("for testing a PC you own") and a hard boundary that the tool only writes, not runs, which implicitly routes execution to the sibling. It stops short of naming flipper_badusb_run as the explicit next step or stating when-not-to-use conditions beyond the ownership caveat.

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