Control mouse and keyboard

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

Annotations already disclose destructiveHint=true, and the description adds a safety-oriented workflow (screenshot before and after) that goes beyond the annotation. It does not explain all potential side effects, but the verification protocol is valuable 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?

Two sentences that are compact, front-loaded with action types and workflow, and contain no unnecessary words.

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?

The description gives a clear workflow and enumerates action types, but the complex actions array with many nested properties and enums is not parameterized. Since there is no output schema, the verify-screenshot guidance helps, but gaps remain for a tool of this complexity.

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 has one 'actions' parameter with zero description coverage, and the description only lists action categories (mouse, keyboard, text, scrolling, wait). It does not explain key fields like x, y, key, text, delta, button, or milliseconds, failing to compensate for the schema's lack of descriptions.

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 sends mouse, keyboard, text, scrolling, and wait actions to the interactive Windows desktop. This specific verb+resource combination distinguishes it from sibling tools like exec, screenshot, or window_control.

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 gives clear usage context, though it does not explicitly mention when not to use the tool or alternatives.

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