Skip to main content
Glama
Sign In
waydroid-mcp

waydroid-mcp

by TechyAditya
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

screenshot

Read-only

Capture an app's display or Waydroid's main display as an image, saving a full-resolution PNG for visual inspection and debugging.

Instructions

Screenshot of an app's display or of Waydroid's main display, returned as an image and saved as a full-resolution PNG. Tap coordinates are display pixels: when the image is scaled down, divide image coordinates by the scale it reports.

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
packageNoApp to act on. An app in its own window or hidden display is found by package; otherwise Waydroid's main display is used.
wait_msNoWait this long first, for a page change or animation after input.
max_sizeNoLongest side of the returned image in pixels; 0 returns full size.
display_idNoAndroid display id instead of a package; 0 is Waydroid's main display.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

The readOnlyHint=true annotation is consistent with taking a screenshot, and the description usefully adds a side effect (a full-resolution PNG is saved) plus a coordinate-scaling caveat. It does not say where the PNG is saved, how the scale factor is reported back, or what happens when the requested display/app is not visible, so meaningful gaps remain beyond the annotation.

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 sentences, front-loaded with what the tool produces, followed by the single non-obvious operational gotcha. No filler or redundant restatement of the tool name.

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?

Return behavior is described (image plus saved PNG), which compensates for the missing output schema, and the coordinate caveat covers the main practical pitfall. What is missing is the PNG location and the interaction between package and display_id when both are supplied, which matters for a 4-parameter tool with no required fields.

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%, so package, wait_ms, max_size, and display_id are already fully documented and the baseline is 3. The description adds only an indirect gloss on max_size via the downscaling/coordinate-division note, without tying it to any named parameter or specifying precedence between package and display_id.

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 states a specific verb and resource ('Screenshot of an app's display or of Waydroid's main display') and clarifies that the result is both returned as an image and saved as a full-resolution PNG. It scopes the two targeting modes (app vs. main display) but does not name or distinguish a sibling such as record_screen or ui_tree.

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 implied by the capture semantics, and the coordinate-scaling note hints at the follow-up workflow with tap/input tools. However, there is no explicit when-to-use statement, no exclusions, and no routing to alternatives like ui_tree for structured inspection or record_screen for video.

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