Skip to main content
Glama

desktop_mouse_down

Presses and holds a mouse button at given screen coordinates to initiate drag or press actions; in stateless mode it fails closed, so use a click or drag tool instead.

Instructions

agent-desktop mouse-down: Press mouse button at coordinates (fails closed in stateless mode; use mouse-click or drag)

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": {
      "xy": "<xy>"
    },
    "name": "desktop_mouse_down"
  }
}

Input Schema

NameRequiredDescriptionDefault
xyYesAbsolute coordinates as x,y; requires --headed; write a negative value with = (--xy=-100,50)
buttonNoMouse button: left, right, middleleft
modifiersNoHeld modifiers: shift, meta, ctrl, alt (repeatable; cmd is accepted)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It usefully discloses the stateless-mode failure behavior, but does not explain the held-button lifecycle, whether a matching mouse-up is required, or what happens on failure. This is meaningful context but not a complete behavioral picture.

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 definition is one front-loaded sentence with a compact parenthetical, and every clause adds useful information. There is no redundant explanation or repetition of schema details.

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

Completeness4/5

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

For a low-parameter desktop input action with a fully documented schema and no output schema, the description covers the core action, a key failure mode, and alternatives. The main remaining gap is the lifecycle expectation that this low-level down action likely pairs with mouse-up, but the name and sibling context make that reasonably inferable.

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 description coverage is 100%, and the schema already documents xy, button, and modifiers in detail. The description adds no parameter-specific meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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

Purpose5/5

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

The description states a specific verb and resource: 'Press mouse button at coordinates.' It also explicitly names mouse-click and drag as alternatives in stateless mode, helping distinguish this low-level press action from compound siblings. The action is clear enough for an agent to understand without opening the schema.

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?

The parenthetical gives a concrete when-not condition: it 'fails closed in stateless mode' and directs callers to 'use mouse-click or drag' instead. This is useful routing guidance, though it does not explicitly state the positive condition (use when stateful mode is available and the button must be held).

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