Robot Actions — Remote Device Control

webpage_get_dom

Get the rendered outer HTML of the web page open in the device browser — works on BOTH iOS (Safari, via the Web Inspector) and Android (Chrome, via CDP); the platform is auto-detected from the udid. Returns document.documentElement.outerHTML, or the outerHTML of a CSS-selector-matched element when selector is given. On iOS, Safari is launched automatically if it is not already open. Output is capped at 100 000 characters with a truncation notice. This is web-page HTML — for a NATIVE app UI hierarchy use device_page_source (Android) or ios_page_source (iOS).

Input Schema

TableJSON Schema

Name	Required	Description
`udid`	Yes	Device UDID / serial (iOS or Android)
`pageId`	No	Target page/tab id — auto-picked when omitted (iOS: appIdKey.pageIdKey; Android: CDP target id)
`socket`	No	Android only: abstract unix socket name (default: chrome_devtools_remote)
`selector`	No	Optional CSS selector — returns outerHTML of the first matching element, or null
`platformVersion`	No	iOS only: platform version for the remote debugger (default: 17.0)

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations provided, the description carries full responsibility for disclosing behavior. It transparently covers cross-platform operation (Web Inspector/CDP), return format (documentElement.outerHTML or selector-matched element), automatic Safari launch on iOS, and the 100,000-character output cap with truncation notice. This is thorough and exceeds what annotations would typically provide.

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

Conciseness4/5

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

The description is moderately sized but information-dense. It front-loads the main purpose and uses parentheticals for supporting details. Each sentence contributes useful information (platform support, return type, iOS behavior, output limit, alternatives). Slightly verbose with the enumerated protocol details, but overall efficient.

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

Completeness5/5

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

Given the tool has no output schema and no annotations, the description fully specifies the return value and output constraints. It also explains platform support, selector behavior, and points to native alternatives. This is comprehensive enough for an agent to understand what the tool returns, when to use it, and its limitations.

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?

The input schema already provides 100% coverage with descriptions for all five parameters, so the baseline is 3. The description adds minimal extra parameter meaning—mentioning that platform is auto-detected from udid and that selector returns the first matching element's outerHTML. However, the schema already documents these aspects, so the description does not significantly enhance parameter understanding.

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

Purpose5/5

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

The description clearly states the tool's verb and resource: 'Get the rendered outer HTML of the web page open in the device browser'. It also distinguishes itself from native UI hierarchy tools and works on both iOS and Android, making its scope unambiguous relative to sibling tools.

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

Usage Guidelines5/5

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

The description explicitly states when to use this tool (for web-page HTML) and provides direct alternatives for native UI: 'for a NATIVE app UI hierarchy use device_page_source (Android) or ios_page_source (iOS)'. It also clarifies platform auto-detection and iOS-specific launch behavior, giving clear usage context.

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

All Robot Actions — Remote Device Control tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0

Disambiguation2/5

The set contains near-identical duplicate families: web_* and playwright_* expose ~15 pairs of the same desktop-grid-browser operations (web_get_text/playwright_get_text, web_reload/playwright_reload), and screenshot/log/network/mock capabilities each have 5-8 entry points (device_screenshot vs android_mjpeg_screenshot vs ios_screenshot vs ios_fast_screenshot vs web_screenshot vs webpage_screenshot vs session_screenshot). Many individual descriptions carefully draw boundaries (devtools vs traffic, HID vs session), but an agent cannot reliably distinguish web_* from playwright_*, and ios_screenshot/ios_fast_screenshot/ios_mjpeg_screenshot blur together.

Naming Consistency2/5

The prefix scheme is broken: Android functionality is split arbitrarily between android_* and device_* (device_screenshot vs android_mjpeg_screenshot), the desktop browser gets two parallel prefixes (web_* and playwright_*), and verbs vary across equivalents (device_navigate_url vs web_navigate vs ios_safari_navigate). session_* uses bare verbs (session_url, session_back), and the same concept gets different names (ios_clipboard_get_hid vs ios_get_pasteboard; device_screen vs ios_orientation).

Tool Count1/5

333 tools is an extreme count by any measure — far beyond the 50+ threshold — and much of the bulk is duplicative (the web_*/playwright_* pairs alone double ~15 slots) or out-of-scope for a device-control server (TestRail, Jira, AzDO, agent memory, secret variables, feedback). Even granting that remote device control + test automation is a broad domain, this surface will devastate agent context budgets and is impossible to navigate coherently.

Completeness4/5

The core device-control and test-automation domain is remarkably thorough: Android and iOS each have full interaction, app-lifecycle, file, network/proxy, performance, crash, accessibility, recording, and replay coverage, with CRUD lifecycles for flows, suites, app uploads, TestRail cases, and visual-review baselines. Minor gaps exist at the margins — Jira/AzDO lack update/transition/comment operations, and iOS cannot open/close tabs — but the central workflows have no dead ends.

Resources

Need Help?