Skip to main content
Glama
Sign In
phonedriver

phonedriver

by hridaya423
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

screenshot

Captures screen images when text snapshots miss canvas, map, or photo content, and optionally marks tappable elements with @ref boxes for accurate interaction.

Instructions

Image of the screen, for what the snapshot lacks (canvas, map, photo). marks boxes tappable elements with their @ref.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
marksNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses the return medium (an image) and the effect of `marks` on output content, but says nothing about encoding/format, image dimensions, payload size, or whether capture is device-wide or app-scoped — meaningful gaps for a screenshot tool with zero structured coverage.

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?

Two tight sentences with no filler; the differentiator from `snapshot` is front-loaded and the parameter explanation follows immediately after. Every clause carries information.

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 one-optional-parameter tool with no output schema, the description covers purpose, sibling differentiation, and the parameter's visible effect — enough to call it correctly. The remaining omission is image format/encoding, which is a minor gap at this complexity.

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 0%, so the description must explain the single boolean. It does: `marks` overlays boxes on tappable elements annotated with their @ref, which tells the agent both what the flag does and what extra data appears in the image. It stops short of saying when to enable it.

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 the specific resource returned ('Image of the screen') and differentiates it from the sibling `snapshot` by naming the cases snapshot cannot handle: canvas, map, photo. An agent can tell these two apart without opening either schema, though the tool name itself is the only verb-like signal.

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 clear selection rule: use this for content the snapshot lacks, with three concrete examples (canvas, map, photo). It does not state an explicit when-not or what the snapshot should be preferred for, but the contrast is clear enough to route correctly.

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