mouse

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

With no annotations, the description carries the full burden. It discloses the coordinate-based approach and the screenshot prerequisite, but omits details about coordinate system (screen vs viewport), potential side effects of mouse actions, or any irreversibility/safety notes beyond what the schema's confirm parameter implies.

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, front-loaded with purpose and usage, with no wasted words. Every clause adds meaningful context.

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 tool has 4 parameters, no output schema, and no annotations. The description provides basic purpose and a key prerequisite but lacks comprehensive information on coordinate system, action semantics, error handling, or safety flags. It feels incomplete for a tool with 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?

Schema coverage is only 25% (only 'confirm' has a description). The description adds context that x/y are based on screenshot coordinates, but it does not explain the 'action' enum values or the 'confirm' parameter beyond what the schema provides. It partially compensates but leaves gaps.

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 it performs coordinate-based mouse control for non-accessible elements, using a specific verb and target context. It distinguishes itself from sibling tools like click and press by focusing on unaccessible surfaces.

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 explicitly indicates when to use the tool (for canvas, maps, custom widgets with no accessible element) and instructs to take a screenshot first. It doesn't explicitly name alternative tools, but the 'no accessible element' condition implies when other tools would be unsuitable.

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