Robot Actions — Remote Device Control

ios_voiceover_preview

Approximate what VoiceOver would announce for each element on the CURRENT screen, and flag announcements a blind user could not act on — unlabelled controls that speak only as "button", labels that read as code identifiers, tappable elements with no Button/Link trait, controls VoiceOver cannot reach at all, and duplicate labels that cannot be told apart by ear. IMPORTANT: this is a RECONSTRUCTION from element attributes, not a transcript. Real VoiceOver speech can only be read from the device on iOS 27+; below that the system cannot be asked what it would say. The accessibility HINT is never included (Apple does not expose it to XCTest at all), role words are the English defaults, and reading ORDER is document order, which is not VoiceOver's geometric order. Treat the wording as indicative and the flagged issues as real. Complements ios_accessibility_audit, which reports Apple's own findings. Requires an active iOS automation session (auto-starts if needed).

Input Schema

TableJSON Schema

Name	Required	Description
`udid`	Yes	iOS device UDID
`element`	No	Narrow to one element by accessibility label, resolved the same way ios_tap_by_label resolves it.
`onlyIssues`	No	Return only elements with a flagged problem, skipping ones that announce fine. Default false.

TDQS

A4.6/5.0

Behavior5/5

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

No annotations are provided, so the description carries full burden. It discloses key limitations: reconstruction not transcript, iOS 27+ requirement, no accessibility hint, English default role words, document order vs geometric order, and caveat that wording is indicative while flagged issues are real. This is far beyond typical descriptions.

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 a single, dense paragraph but is well-structured: purpose first, then important limitations, then relationship to sibling. Every sentence adds essential information for correct use; no filler.

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?

For a tool with no output schema and no annotations, the description explains purpose, output semantics, limitations, and requirements. It could be slightly more explicit about the return format, but the flagged issues are enumerated. Overall, highly complete.

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?

Input schema covers all three parameters with descriptions (100% coverage). The description does not add parameter-level detail; the schema already explains udid, element, and onlyIssues. Baseline 3 is appropriate since schema does the heavy lifting.

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 opens with a specific action: 'Approximate what VoiceOver would announce for each element... and flag announcements' — clear verb+resource. It distinguishes from sibling ios_accessibility_audit by noting it is a 'RECONSTRUCTION' and 'Complements ios_accessibility_audit, which reports Apple's own findings.'

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?

Explicitly names the complementary sibling 'ios_accessibility_audit' and differentiates the two. Also states requirement: 'Requires an active iOS automation session (auto-starts if needed).' This gives the agent clear context for when to use this tool.

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?