kvm_keystroke

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

With no annotations provided, the description carries the full burden and does substantial work: it discloses single-keystroke scope, the KeyboardEvent.code encoding, optional modifier combination, and the fact that a screenshot is captured after the key is sent. It does not state whether a device must be selected first or whether the key is auto-released, both relevant given the kvm_select_device and kvm_key_hold siblings.

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?

Three short segments in roughly 25 words: the action and its encoding, the return value, and the input-tier tag. Every clause earns its place, and the most critical information (what to send and in what format) is front-loaded.

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 9-parameter tool with zero schema descriptions, no annotations, and no output schema, the description covers the essentials for a correct call: code format, modifier semantics, and the screenshot return. The notable omissions are the device-selection prerequisite (kvm_select_device exists as a sibling) and the screenshot return format, but the tool's simplicity keeps these from being fatal.

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 coverage is 0%, so the description must compensate, and it does: 'KeyboardEvent.code' supplies the exact vocabulary for the `code` parameter, which the schema leaves as a bare string—this is the difference between sending 'KeyR' and an unusable guess. 'With optional modifiers' explains the role of all 8 boolean modifier parameters, though the left/right distinction is left to the parameter names.

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?

Names the exact verb and resource: 'Send one KeyboardEvent.code keystroke' with concrete examples (Enter, Escape, Tab, KeyR, F7), which pins down the semantic domain precisely. The return-value clause ('Returns a post-key screenshot') further helps the agent distinguish it from kvm_paste, kvm_mouse, and kvm_screenshot.

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 word 'one' and the discrete key examples imply this is for single key taps, contrasting implicitly with kvm_key_hold/kvm_key_release for sustained presses and kvm_paste for text strings. However, the description never explicitly says when to prefer this tool over those alternatives, so routing is left to inference.

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