Robot Actions — Remote Device Control

ios_tap_by_label

PREFERRED way to tap on iOS: find a UI element by its accessibility label and tap it in one call via the automation session. No coordinate math, and it works on zero-area elements (e.g. bottom-tab labels) where ios_tap(x,y) would miss. Use this before falling back to ios_tap with raw coordinates. If the element is off-screen it auto-scrolls to bring it into view first (disable with autoScroll:false). On no match, returns similar labels (incl. off-screen) to retry with. Requires an active iOS automation session (auto-starts if needed).

Input Schema

TableJSON Schema

Name	Required	Description
`udid`	Yes	iOS device UDID
`label`	Yes	Accessibility label or visible text of the element to tap
`match`	No	How to match `label`. Default "contains" — strict, and the only modes that act without interpretation. "fuzzy" tolerates typos and word-order drift, and is tried ONLY after strict finds nothing; it REFUSES when two candidates are too close rather than guessing between them (e.g. "Sign" vs Sign In / Sign Out), and reports which attribute it matched.
`autoScroll`	No	Scroll the element into view if off-screen before tapping (default: true)

TDQS

A4.7/5.0

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 auto-scroll behavior (with disable option), behavior on no match (returns similar labels), and the requirement for an active iOS automation session (auto-starts if needed). This covers key behavioral traits comprehensively.

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?

Four sentences front-load the core purpose and key differentiator. Every sentence adds value: preferred method, no coordinate math, zero-area elements, fallback hint, auto-scroll behavior, no-match feedback, session requirement. No wasted words.

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?

For a tool with 4 parameters and no output schema, the description covers when to use, parameter behavior, edge cases (off-screen, no match), and prerequisites (active session). It leaves no significant gaps given the tool's complexity.

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?

Schema description coverage is 100%, so baseline is 3. The description adds modest extra context for the `match` parameter (explaining fallback and refusal logic) but does not significantly enhance understanding of the label or autoScroll parameters beyond the schema descriptions. No value added beyond what the schema already conveys.

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 taps a UI element by its accessibility label in one call, distinguishing it from coordinate-based alternatives like ios_tap. The phrase 'PREFERRED way to tap on iOS' sets clear context.

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 instructs to use this before falling back to ios_tap with raw coordinates. Mentions it works on zero-area elements where coordinate taps fail, and on no match it returns similar labels to retry. Provides clear when-to-use guidance.

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?