capture_start

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

No annotations are provided, so the description carries the full burden, and it discloses very little: it doesn't say the capture runs until capture_stop, whether `out` is overwritten or appended, or what privileges are needed. The platform backend note is the only added behavioral context.

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?

A single front-loaded sentence with zero filler; the action and destination are stated immediately. Nothing could be trimmed without losing information.

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?

An output schema exists, so return values needn't be described, but for a stateful capture-start operation with no annotations and 0% parameter coverage, the definition omits essentials such as capture duration/lifecycle, privilege requirements, and the meaning of `bus`.

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?

Schema description coverage is 0%, so both parameters rely on the description. It references `out` as the destination file (adding some meaning), but `bus` is never mentioned at all, leaving its default of 0 and its selection semantics entirely unexplained.

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?

States a specific verb+resource ("Start capturing USB traffic") and even names the platform backends (usbmon/USBPcap), which is genuinely informative. It doesn't explicitly contrast with its obvious sibling capture_stop, but the verb makes the distinction self-evident.

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?

No guidance on when to call this versus alternatives, nor any prerequisites. For a capture tool that typically requires elevated privileges (usbmon needs root, USBPcap needs a driver install), the absence of any setup condition is a real gap.

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