Skip to main content
Glama
Sign In
OpenCU

OpenCU

by Daily-AC
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

drag

Move a selection over a fresh app-window screenshot to capture a specific region and return the updated screenshot and state for verification.

Instructions

Drag inside the fresh app-window screenshot and return a new screenshot and state. To crop a side while preserving height: zoom out for margins, Select All, then move only the middle left/right selection handle horizontally. Keep the existing top/bottom selection edges; verify dimensions in Inspector. Window borders resize the window.

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": {
      "app": "<app>",
      "from_x": "<from_x>",
      "from_y": "<from_y>",
      "to_x": "<to_x>",
      "to_y": "<to_y>"
    },
    "name": "drag"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYesApp name or full app path; macOS bundle ID; macOS and Windows pid:<pid>; Windows process name, window title fragment, or Start-menu shortcut name; Linux desktop entry name, executable name or window title fragment
to_xYes
to_yYes
scopeNomacOS and Windows: element index from the latest returned state. Read only its retained subtree, renumbered from [1], including after actions. If it disappears, return the whole window with a notice. Linux returns INVALID_ARGUMENT.
from_xYes
from_yYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false and openWorldHint=true, so the agent already knows this is a mutating, open-world action. The description usefully adds that it returns a fresh screenshot and state (no output schema exists), but it omits what the gesture actually changes, whether coordinates are pixel or logical units, and whether the drag is press-move-release.

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

Conciseness3/5

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

The lead sentence is well front-loaded and earns its place. However, the three following sentences are a niche cropping walkthrough with references to UI concepts outside this server, consuming most of the description's length without serving the general drag operation.

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 6-parameter mutating tool with no output schema, the description does disclose the return shape (screenshot + state), which is the biggest structural gap. It still leaves coordinate semantics and the effect of the drag unstated, and spends its remaining space on scenario-specific advice rather than closing those gaps.

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

Parameters2/5

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

Schema description coverage is only 33%: from_x, from_y, to_x, and to_y are completely undocumented, and only app and scope carry descriptions. The phrase 'inside the fresh app-window screenshot' hints that coordinates are screenshot-relative, but it never states units, origin, or whether values are window- or image-space, leaving the four required coordinate parameters underspecified.

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 first sentence names a specific verb (drag) and resource (inside the fresh app-window screenshot) plus the return value (a new screenshot and state), which is enough to distinguish it from click/scroll siblings. It stops short of explicitly contrasting itself with those siblings, so it is clear but not fully differentiated.

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

Usage Guidelines2/5

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

There is no explicit statement of when to choose drag over click, scroll, or perform_secondary_action, nor any preconditions (e.g. needing a prior get_app_state screenshot). The only procedural text is a narrow image-cropping recipe referencing 'Select All', 'zoom out', and 'Inspector', which are not actions in this toolset and are unlikely to generalize, making it more confusing than guiding.

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

Deploy Server

Other Tools