Skip to main content
Glama

pointer

Perform mouse actions—move, click, drag, scroll—on Hyprland desktops. Use global coordinates or target a window with relative percentages to maintain accuracy even if the window moves or resizes.

Instructions

Mouse. action='move' (x,y) | 'click' (optional x,y first; button left/right/middle; double=true) | 'drag' (x,y → to_x,to_y holding button) | 'scroll' (scroll_dy notches, positive = content down; optional x,y first).

Coordinates are GLOBAL logical pixels by default. Pass window (address, class/title substring, or a description like "the file browser") plus x_pct/y_pct in 0.0–1.0 to click RELATIVE to that window instead: (0.5,0.5) is its centre, (0.1,0.05) near its top-left. The window is focused first. This is the robust form — it survives the window moving or resizing.

then appends the result to this call so you skip a round-trip: 'desktop' a fresh snapshot, 'screenshot' a stable capture, 'ui' the focused window's elements with current values, 'none' (default) nothing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNo
yNo
thenNonone
to_xNo
to_yNo
x_pctNo
y_pctNo
actionYes
buttonNoleft
doubleNo
windowNo
to_x_pctNo
to_y_pctNo
scroll_dxNo
scroll_dyNo
allow_authNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and handles it well: it discloses coordinate defaults, window focusing, scroll direction sign, double-click support, and exactly what `then` returns. It does not explain allow_auth or potential side effects of authentication, but core mouse behavior is transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with a compact action grammar, then expands coordinate semantics and `then` behavior in clear, short sections. It is dense but not padded; every sentence adds operational value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 16-parameter tool with no annotations and no schema descriptions, the description covers the main actions and coordinate modes well, and an output schema exists to cover return values. It is not fully complete because to_x_pct/to_y_pct, scroll_dx, and allow_auth remain unexplained, leaving several schema properties opaque.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description compensates by explaining most parameters: action values, x/y, to_x/to_y, button, double, scroll_dy, x_pct/y_pct, window, and then. It leaves to_x_pct/to_y_pct, scroll_dx, and allow_auth undocumented, which is a meaningful but secondary gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description defines the tool as a mouse control with a clear action grammar: move, click, drag, and scroll, including coordinate semantics. It is clearly a pointer/mouse tool, but it does not explicitly differentiate itself from sibling input tools like click_ui or keyboard.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives strong within-tool guidance: global pixels by default versus window-relative percentages, explains that the window is focused first, and calls the relative form robust because it survives window movement or resizing. However, it never says when to choose pointer over sibling tools such as click_ui or keyboard, so cross-tool selection guidance is implied rather than explicit.

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