Control mouse and keyboard

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

The annotations indicate destructiveHint=true, and the description appropriately warns that actions affect the live desktop. It adds operational context by recommending a screenshot-verify loop, which goes beyond the annotations. However, it does not detail all potential destructive outcomes (e.g., keystrokes affecting unsaved work) or permission/security implications.

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 two sentences and immediately fronts the core behavior. Every word adds value: the first sentence identifies the input categories, the second provides the exact workflow. No fluff or redundant restating of the tool name.

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 tool with one complex parameter, nested objects, no output schema, and destructive annotations, the description is reasonably complete. It tells the agent what to do (send actions) and how to use it safely (screenshot first, verify after). However, it lacks explicit details on when not to use it or how the wait action works relative to screen transitions.

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 the description carries the burden. It lists action types (mouse, keyboard, text, scrolling, wait) and gives workflow hints, but it does not explain individual fields like x, y, delta, button, milliseconds, or key formats. The enum values in the schema are self-explanatory for an AI agent, and the description covers the high-level categories, but some parameter semantics remain implicit.

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 the tool's purpose: sending mouse, keyboard, text, scrolling, and wait actions to the interactive Windows desktop. It lists specific action categories and distinguishes itself from sibling tools like browser_control and window_control by targeting the desktop-level input.

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 provides an explicit workflow: take a screenshot first, focus the target window, act, then screenshot again to verify. This implies when to use the tool (for interactive desktop manipulation) but does not explicitly state exclusions or mention alternative tools for specific scenarios.

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