mouse_down

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

Annotations only include false hints, so the description carries the burden. It discloses two important behaviors: the VM remains locked after this call until vm_unlock, and the button must be released later. This goes beyond what annotations provide.

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?

Two sentences, no wasted words. The first sentence states the core action, and the second gives essential follow-up instructions. Information is front-loaded and easy to scan.

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 mouse input tool, the description covers the action, optional coordinates, necessary release, and the VM lock side effect. It lacks detail about return values, but no output schema exists and the tool is simple. The pairing with vm_unlock is a key completeness element.

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?

The schema already documents x and y as 'Zero-based physical screen coordinate.' The description adds that moving to coordinates is optional, but does not explain the button parameter, which is only covered by its enum. With 67% schema coverage, the description offers modest added value.

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?

Description clearly states the action: 'Hold a mouse button down' with optional coordinate movement. This distinguishes it from siblings like mouse_click, mouse_up, and mouse_move, which perform related but different actions.

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?

Provides clear usage context by instructing to 'Always release it later' and noting the VM lock with 'call vm_unlock when finished.' It implies a paired workflow with mouse_up but does not explicitly contrast with alternative tools like mouse_click.

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