Drag between start and end coordinates on a Raspberry Pi Wayland desktop over SSH, then capture a fresh screenshot to confirm the result.
Drag in original desktop pixels, or image pixels with the current view_id, then show a fresh screenshot.
| Name | Required | Description | Default |
|---|---|---|---|
| end_x | Yes | ||
| end_y | Yes | ||
| start_x | Yes | ||
| start_y | Yes | ||
| view_id | No | ||
| capture_max_width | No |
Changes observed during successful MCP inspections.
v0.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior the annotations lack: coordinates may be given in original desktop pixels or image pixels relative to the current view_id, and a fresh screenshot is returned afterward. It still omits what state the drag alters or any permission/side-effect detail.
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?
A single front-loaded sentence with no filler; the coordinate-frame rule comes first and the screenshot consequence last. It is dense but slightly cryptic, so not quite maximal.
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 destructive, open-world UI-automation tool with no output schema, the description covers the return behavior (fresh screenshot) and the coordinate-frame choice, which is the most important decision. However, with 0% schema coverage it leaves capture_max_width and drag semantics unexplained, so it is only partially complete.
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% across six parameters, so the schema supplies only bare titles. The description partially compensates by explaining that start/end coordinates are pixels and that view_id selects the image-pixel frame, but capture_max_width and the required start/end pairing semantics remain undocumented.
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?
States a clear verb (drag), the two coordinate frames it accepts, and the post-action screenshot. It implicitly separates itself from desktop_move/desktop_click by describing a full drag path (start to end) rather than a single-point or continuous move. It stops short of explicitly naming the sibling it differs from.
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?
There is no when-to-use guidance and no exclusions. The agent is not told when to prefer desktop_drag over desktop_move (e.g., move-to-position vs press-drag-release), nor any prerequisite such as an active connection or view context. Only the coordinate-frame distinction offers indirect routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.