Skip to main content
Glama

browser_mouse

Read-onlyIdempotent

Low-level mouse at VIEWPORT coordinates (pixels from the top left), for canvases, maps, sliders and anything a selector cannot reach. action: 'move', 'down', 'up', 'click', 'dblclick' (x and y needed for move/click/dblclick; down/up use the current position), 'wheel' (delta_x, delta_y). button: left | right | middle. steps > 1 makes 'move' a smooth path. A drag is: move, down, move, up.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "page_id": "<page_id>",
      "action": "<action>"
    },
    "name": "browser_mouse"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
stepsNo
actionYes
buttonNoleft
delta_xNo
delta_yNo
page_idYes
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, so the safety profile is covered. The description adds genuine behavior that the annotations do not: down/up act on the current cursor position, steps>1 smooths the path, and drags must be built from a composite sequence. It does not discuss how the tool handles coordinate truth (for example, viewport versus page or scroll), or whether clicks wait for the page to settle.

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

Conciseness4/5

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

Dense and front-loaded: the coordinate frame comes first, then the per-action requirements, then the drag recipe. Backticked parameter names make it scannable, though the sentences are tightly packed and read almost like terse notes.

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?

Complete enough for the core interaction, and no output schema means return values need no explanation. Still, for a nine-parameter low-level input tool with almost no schema coverage, leaving page_id and in_workspace unexplained is a real gap.

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

Parameters3/5

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

Schema coverage is only 11%, so the description has to carry most of the parameter meaning, and it does add a lot: the x/y coordinate frame, the valid action values, the dependency that x and y are needed for move/click/dblclick but not down/up, the button values, and the meaning of steps and delta_x/delta_y. However, page_id and in_workspace are never mentioned, and the 'button' values are not tied to any runtime effect.

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?

States a specific verb and resource: low-level mouse events at VIEWPORT pixel coordinates, with a clear scope (canvases, maps, sliders, anything a selector cannot reach). It implicitly separates itself from selector-based siblings, but never names browser_click or browser_drag, even though browser_drag overlaps with the drag recipe given here.

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

Usage Guidelines4/5

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

Gives a usable selection rule: use this when a CSS selector cannot reach the target, and gives a concrete composition recipe ('A drag is: move, down, move, up'). It stops short of explicit exclusions, such as telling the agent to prefer browser_click or browser_drag when a selector does exist.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.