Skip to main content
Glama

drag

Simulate a pointer move from an element ref or x,y coordinates to another point, with optional speed and press/hold timing for precise UI interaction and drop confirmation.

Instructions

Drag between two points, each an element ref (@e5) or raw coordinates (100,200).

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": {
      "from": "<from>",
      "to": "<to>"
    },
    "name": "drag"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesDrag end: element ref (e.g. @e7 or e7) or "x,y" coordinates.
fromYesDrag start: element ref (e.g. @e5 or e5) or "x,y" coordinates.
velocityNoDrag speed in points/sec (default: 500). 100-250 for slow/precise, 1000+ for fast.
session_idNoSession ID to target. Optional: falls back to the MCP-server-held dev_start session, then this project's `vibeview dev --detach` state, if either is available.
hold_durationNoMilliseconds to hold at the destination after the drag (default: 0). Use 500+ for drop confirmation.
press_durationNoMilliseconds to press before the drag starts (default: 60). Use 500+ for long-press reorder.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior2/5

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

Only readOnlyHint=false is supplied, so the description carries most of the burden and adds little: it does not say what the gesture is dispatched against, whether it is reversible, whether the destination must be a valid drop target, or what happens on failure. Beyond restating the input format, the description discloses no behavioral traits of the drag itself.

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?

One front-loaded sentence with zero filler; the core action comes first and the input forms follow immediately.

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 six-parameter gesture tool with no output schema, the description is minimally viable: the schema covers all parameters, but nothing explains the gesture's side effects, prerequisites (a live session/target), or the relationship between press/hold/velocity tuning and real use cases such as long-press reorder versus drop confirmation.

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 100% and every parameter already has a description covering format, defaults, and tuning ranges. The description repeats the ref/coordinate format for from and to, adding no meaning beyond the schema, so the baseline of 3 applies.

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 gives a specific verb and resource ("Drag between two points") and states the accepted address forms inline. An agent can tell it apart from tap or press, though it does not explicitly contrast with swipe, which is the closest sibling and could overlap conceptually.

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?

Usage is only implied by the mechanics: use it when you need a continuous drag from one point to another. There is no explicit when-to-use/when-not guidance, no mention of choosing swipe instead, and no mention of when to raise press_duration or hold_duration (the schema hints at long-press reorder and drop confirmation, but the description never routes the agent there).

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