Robot Actions — Remote Device Control

android_devtools_console_logs

Collect console logs, exceptions, and log entries from a page running on the device for a time window. Enables Runtime and Log domains, then listens for Runtime.consoleAPICalled, Runtime.exceptionThrown, and Log.entryAdded events. Returns a normalized array of { level, text, url?, lineNumber? } entries. This is a LIVE-WINDOW collector: it only captures events fired AFTER it attaches, so triggering the logging from a SEPARATE tool call races the ~1-3s attach latency and is silently missed. To capture logs from an action, pass triggerJs (runs inside the window). Default window: 3 000 ms. Maximum: 15 000 ms. Omit pageId to auto-select the visible/active page.

Input Schema

TableJSON Schema

Name	Required	Description
`udid`	Yes	Device serial number (UDID)
`pageId`	No	Target page id (auto-picked when omitted)
`socket`	No	Abstract unix socket name (default: chrome_devtools_remote)
`triggerJs`	No	JavaScript run INSIDE the collection window (right after the listeners attach) so the logs it produces are captured race-free — e.g. "location.reload()", "document.querySelector('#go').click()", or "console.log('probe')". Prefer this over triggering from a separate call.
`durationMs`	No	Collection window in milliseconds (default: 3000, max: 15000)

TDQS

A4.7/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses the live-window attach behavior, the ~1-3s attach latency, the race condition, and the auto-selection of visible/active page when pageId is omitted. Missing would be explicit statements about what happens with zero events collected (empty array?) or any side effects, but the disclosed behavior is substantial and directly relevant to correct usage.

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?

Well-organized paragraph that front-loads the core purpose before diving into live-window caveats. The critical spatial warning is highlighted in caps ('LIVE-WINDOW collector'), and every sentence earns its place — return format, event types, defaults, pageId auto-selection. No filler or redundancy.

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 time-windowed event collector with no output schema, the description thoroughly covers the attach/race behavior, default limits, triggerJs mechanism, and page selection. The tricky live-window semantics are fully explained, which is precisely the kind of context an agent needs to use this effectively. No significant gaps remain for correct usage.

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 beyond the schema: it explains the triggerJs mechanics ('runs INSIDE the collection window right after the listeners attach ... race-free') with concrete examples, and clarifies the durationMs default/max. The triggerJs semantics in particular are materially enhanced beyond the bare schema text.

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?

Specific verb+resource: 'Collect console logs, exceptions, and log entries from a page running on the device for a time window.' Clearly distinguishes from siblings like android_devtools_capture_network (network) and ios_safari_console_logs (iOS platform). States the exact protocol mechanisms (enables Runtime and Log domains, listens for specific events) and the return shape.

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 explains the live-window behavior ('only captures events fired AFTER it attaches') and warns about the race condition when triggering from a separate tool call ('silently missed'). Provides a concrete remedy (pass triggerJs to run inside the window) and documents the default/maximum window. This is model-grade usage guidance for a tool with a subtle temporal gotcha.

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?