mobilerun-mcp

Ui

ui

Capture a raw accessibility tree, phone state, and device context from a connected Android or iOS device so AI agents can inspect screens before tapping or typing.

Instructions

Raw UI snapshot (a11y_tree, phone_state, device_context, ...), as Device.ui().

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": "ui"
  }
}

Input Schema

Name	Required	Description	Default
`device`	No
`filter`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 27, 2026

TDQS

C2.2/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden, and it says almost nothing: it doesn't state that this is a non-destructive read, whether the call can be slow, or how 'filter' changes the returned snapshot. The cryptic 'as Device.ui()' reference is a Python API pointer, not behavioral disclosure.

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?

It is a single front-loaded sentence with no wasted filler, which is good. But the brevity comes at the cost of under-specification rather than genuine economy, and the trailing '...' and 'as Device.ui()' reference add little for an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be re-explained. Still, with zero annotation coverage, 0% parameter documentation, and five-plus competing snapshot siblings, the description leaves the agent unable to decide when or how to invoke this tool correctly.

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

Parameters1/5

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

Schema description coverage is 0% and the description explains neither parameter. The 'filter' boolean defaulting to true is completely opaque — the agent cannot know whether it strips nodes, prunes the tree, or limits the payload — and 'device' (nullable string selector) is likewise unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the resource (a raw UI snapshot) and enumerates some of its contents (a11y_tree, phone_state, device_context), which is more than a tautology of the name 'ui'. However, it gives no verb (fetch/return) and fails to distinguish itself from close siblings like ui_json, ui_with_recovery, or get_ui_tree, so an agent cannot tell which snapshot tool to pick.

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 when-to-use guidance and no mention of alternatives, despite several near-identical siblings (ui_json, ui_with_recovery, get_ui_tree, perceive_screen, read_screen). The agent gets no signal about why it would choose this over those.

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

Deploy Server

Ui