run_badusb

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

The description details the steps (upload to path if content given, then launch and start) and warns of keystroke injection. Annotations already mark destructiveHint=true, and the description adds context about the 'Real action' and approval per call, enhancing transparency beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, using a warning emoji at the start and covering all key points in a single paragraph. It is front-loaded with the essential purpose and warning, but the phrase 'Real action — approve per call' is slightly cryptic.

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

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

For a destructive tool with no output schema and 0% schema coverage, the description adequately explains the workflow (upload, launch, start), the return ('run screen'), and the risk. It covers most gaps but could clarify the return format or error scenarios.

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

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

With 0% schema coverage, the description explains that 'content' is uploaded to 'path' and provides a path example. This adds meaning to both parameters, though it could specify the expected format of content (DuckyScript commands) more precisely.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Run a BadUSB (DuckyScript) payload over BLE' and explains the process (upload content if given, launch app, start). It distinctly identifies the tool's action and resource, differentiating it from sibling tools like storage_write and app_launch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description warns 'YOUR OWN machine / authorized targets ONLY', providing clear usage context and emphasizing the destructive nature. However, it does not explicitly state when to use this tool versus alternatives (e.g., manual file writing + app launch).

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