Robot Actions — Remote Device Control

webpage_snapshot

Read the page as a structured tree of what is on it — works on BOTH iOS Safari and Android Chrome. START HERE before acting: each line is role "name" [ref=eN], and that ref goes straight into webpage_click / webpage_type / webpage_hover, so you never have to guess a CSS selector or read markup. Refs address the live element, so they survive markup that shifted and reach elements no selector can. Shows only what is actually visible by default, and marks disabled / checked / expanded state and current field values. Pass interactiveOnly:true for just the things you can act on, or a selector to scope it to one region of a large page.

Input Schema

TableJSON Schema

Name	Required	Description
`udid`	Yes	Device UDID / serial (iOS or Android)
`limit`	No	Maximum nodes to return (default: 400, max: 2000)
`pageId`	No	Target page/tab id — auto-picked when omitted
`socket`	No	Android only: abstract unix socket name (default: chrome_devtools_remote)
`selector`	No	CSS selector to scope the snapshot to (default: the whole page)
`includeHidden`	No	Include elements that are not visible (default: false)
`interactiveOnly`	No	Only links, buttons, fields and other actionable roles (default: false)
`platformVersion`	No	Ignored (kept for compatibility)

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so well. It discloses the default visibility behavior, state annotations (disabled/checked/expanded), live refs that survive markup changes, and platform compatibility. This is thorough for a read-only tool, though it omits error/rate-limit details.

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?

The description is dense but efficient, front-loading the core purpose and workflow. Every sentence contributes actionable information—output format, platform support, parameter tips, and behavior—without unnecessary verbosity.

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?

Since there is no output schema, the description explains the return format and state markers, which is crucial. It also covers platform support, usage workflow, and key configuration options, making it reasonably complete for a snapshot tool with eight parameters.

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%, setting a baseline of 3. The description adds value by explaining the purpose of `interactiveOnly` and `selector` beyond their schema descriptions, helping the agent choose appropriate scoping. It does not add meaning to the other six params, but the baseline is already sufficient.

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 reads a page as a structured tree of visible elements, specifies the output format (`role "name" [ref=eN]`), and highlights platform support for iOS Safari and Android Chrome. It differentiates from siblings by explaining how refs integrate with interaction tools, making its purpose unambiguous.

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 gives strong usage guidance: 'START HERE before acting' and explains how refs feed into webpage_click/type/hover. It also advises when to use interactiveOnly or a selector. However, it does not explicitly name alternative tools or when-not-to-use scenarios, so it falls short of a 5.

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?