Robot Actions — Remote Device Control

webpage_screenshot

Screenshot the web page in the device browser (iOS Safari or Android Chrome, auto-detected). ANDROID: a clean capture of the web CONTENT — pass selector or ref to capture just that element (scrolled into view). iOS: element-clipped web capture is unavailable, so this returns the full DEVICE frame (includes the Safari chrome/status bar); selector/ref clipping is Android-only and is ignored on iOS (a note is returned). Returns a JPEG image.

Input Schema

TableJSON Schema

Name	Required	Description
`ref`	No	Android only: capture just this element, named by a ref from a page-elements listing
`udid`	Yes	Device UDID / serial (iOS or Android)
`pageId`	No	Target page/tab id — auto-picked when omitted
`socket`	No	Android only: abstract unix socket name (default: chrome_devtools_remote)
`selector`	No	Android only: capture just this element (CSS selector), scrolled into view
`platformVersion`	No	Ignored (kept for compatibility)

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations, the description fully discloses behavior: Android captures content, iOS includes Safari chrome/status bar, selector/ref are Android-only and ignored on iOS with a note returned, and output is a JPEG image. This goes beyond minimal expectations and covers both platform differences and edge cases.

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 compact and front-loaded with the main purpose. The two sentences pack significant detail without redundancy, though the second sentence is long and could be split for readability, but every clause adds value.

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?

Given the tool's complexity (platform differences, 6 parameters, no output schema), the description covers the core behavior, return type, and platform-specific limitations. It doesn't explain error scenarios like invalid selectors, but the provided details are sufficient for most use cases.

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 100%, so the baseline is 3. The description adds important semantic context beyond the schema by clarifying that selector/ref are Android-only and ignored on iOS, and that platformVersion is ignored for compatibility, which helps the agent avoid incorrect usage.

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 purpose: 'Screenshot the web page in the device browser (iOS Safari or Android Chrome, auto-detected).' This is a specific verb+resource combination that distinguishes it from sibling screenshot tools like device_screenshot and web_screenshot by scoping to the mobile browser.

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?

The description implies when to use it (mobile web screenshots) and clearly explains platform-specific behavior, e.g., Android can capture elements with selector/ref, while iOS cannot and returns a full device frame. It doesn't explicitly name alternatives, but the context is strong enough for an agent to choose this tool over generic screenshot tools.

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?