Skip to main content
Glama
Mobile Next MCP Server

Mobile Next MCP Server

Official
by mobile-next

Drag On Screen

mobile_drag_on_screen

Drag a finger between coordinates or element refs on a mobile screen to move sliders, reorder lists, or perform drag-and-drop actions.

Instructions

Drag one finger from one point to another, e.g. to move a slider, reorder a list or drag and drop. Each end is either x,y coordinates or an element by its ref (e.g. "@e5") from the latest mobile_list_elements_on_screen result. Prefer ref when the element is listed.

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": {
      "device": "<device>"
    },
    "name": "mobile_drag_on_screen"
  }
}

Input Schema

NameRequiredDescriptionDefault
x1NoThe x coordinate to start the drag from, in pixels. Required unless fromRef is given
x2NoThe x coordinate to end the drag at, in pixels. Required unless toRef is given
y1NoThe y coordinate to start the drag from, in pixels. Required unless fromRef is given
y2NoThe y coordinate to end the drag at, in pixels. Required unless toRef is given
holdNoHow long the finger stays down before it moves, in milliseconds. Use it (e.g. 500) to pick up an item that would otherwise scroll. Defaults to 0
toRefNoElement ref to end the drag at, e.g. "@e7". Takes precedence over x2,y2
deviceYesThe device identifier to use. Use mobile_list_available_devices to find which devices are available to you.
fromRefNoElement ref to start the drag from, e.g. "@e5". Takes precedence over x1,y1

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.18

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare this is a mutating (readOnlyHint=false) but non-destructive action in an open-world environment, so the safety profile is covered. The description adds no side-effect context beyond the mechanical motion — nothing about needing an unlocked/foregrounded screen, whether the drag can trigger unintended gestures, or timing behavior. It restates the action rather than disclosing consequences.

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?

Three short sentences with the action front-loaded, then endpoint flexibility, then the ref-sourcing rule and preference. Nothing is redundant and no sentence could be dropped without losing a constraint.

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 an 8-parameter gesture tool with full schema coverage and annotations, the description covers what an agent needs: motion semantics, dual endpoint modes, and where refs come from. It omits any mention of device targeting or failure behavior, but the device parameter is documented in-schema and no output schema exists to explain.

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 coverage is 100%, so the baseline is 3, but the description adds genuine cross-tool semantics: each endpoint may be coordinates OR a ref, and that ref must come from the latest mobile_list_elements_on_screen result. That sourcing constraint is not stated in the schema and directly affects how an agent obtains a valid fromRef/toRef.

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 ("Drag one finger from one point to another") and grounds it with concrete use cases: sliders, list reordering, drag-and-drop. It is clearly distinguishable from tap/long-press siblings, though it never explicitly contrasts itself with mobile_swipe_on_screen, which is the nearest neighbor.

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 clear situational context via the enumerated use cases and an explicit preference rule ("Prefer ref when the element is listed"). It does not state when to choose this over mobile_swipe_on_screen or mobile_long_press_on_screen_at_coordinates, so there is no exclusion guidance.

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