mouse

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

Beyond the destructiveHint annotation, the description discloses critical behaviors: click refs are enforced with refusal conditions (host reboot, media swap, age >60s, foreign ref), move-only bypasses the ref requirement, coord_space affects coordinate interpretation across resolution changes, and the tool is gated by a runtime flag plus per-invocation approval. This is substantive transparency about side effects and preconditions.

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 front-loaded with the core purpose, then organized into precise technical constraints with no wasted words. It is dense but readable; each statement adds value. Slightly long, but acceptable given the safety-critical details.

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 mutating HID tool with no output schema, the description covers what an agent needs to know: destructive classification, ref staleness rules, coordinate space semantics, move-only behavior, and gating conditions. The only minor omission is the meaning of 'confirm' and 'profile', but the overall context is robust for correct invocation.

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 description coverage, the description compensates by clarifying key parameters: coord_space values and default, observed_frame_ref requirements for clicks, and button omission meaning move-only. However, 'confirm' and 'profile' are not semantically explained, so the agent still has to guess their effects — leaving a meaningful gap.

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 opens with a clear, specific verb+resource statement: 'Move the mouse (and optionally click) on the host.' It immediately distinguishes this from sibling input tools (press_key, type_text, send_shortcut) by the target device and action, and mentions the DESTRUCTIVE HID input nature, giving the agent a strong cue for when to select this tool.

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?

It explains when a click requires an observed_frame_ref and when move-only is permissible, and notes the tool is gated by KVM_PILOT_MCP_ALLOW_HID and approval. This is clear usage context, though it does not explicitly name alternative tools or state 'use this instead of X' — the context alone is sufficient to differentiate.

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