Locate a UI element by visual description and click it automatically, returning coordinates and click result. Combines visual search and mouse click into one step for desktop automation.
定位目标并点击一步完成：先视觉定位（多阶段精定位），再鼠标单击。返回定位坐标与点击结果。
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | 要点击的目标描述 | |
| hold_ms | No | 按压时长（默认120） | |
| image_path | No | 截图路径（可选） |
Changes observed during successful MCP inspections.
v2.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the order of operations (visual localization then click), mentions multi-stage precision, and states it returns coordinates and click result. However, it does not disclose potential failure modes (e.g., target not found), side effects (e.g., moving the cursor), or any access/permission requirements. This is a gap given no annotation support.
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 a single, front-loaded sentence that conveys the core purpose, the steps, and the return value without redundancy. It is appropriately sized and contains no wasted 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?
For a tool that combines two actions (locate and click) with three parameters, no output schema, and no annotations, the description is minimal. It explains the process and return but lacks usage guidance relative to siblings, error handling, and behavior when the target is not found. This leaves the agent without enough context to fully anticipate the tool's behavior in edge cases.
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 100%, with each parameter (target, hold_ms, image_path) having a description. The tool description adds no additional parameter semantics beyond what the schema provides; it only mentions the overall return value. Therefore, the description does not compensate for any missing schema detail.
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: '定位目标并点击一步完成' (locate target and click in one step), specifying that it first performs visual localization (multi-stage precise localization) then a mouse click, and returns coordinates and click result. This distinguishes it from siblings like desktop_click (click only) and desktop_locate (locate only).
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 implies the tool performs both locate and click, but it does not explicitly state when to use this over the sibling tools. There is no mention that desktop_locate should be used if only coordinates are needed, or that desktop_click should be used if the target is already known. Guidance is only implied by the combined action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.