Robot Actions — Remote Device Control

ios_safari_console_logs

Collect console logs, exceptions, and log entries from a Safari page on an iOS device over a time window. Enables the Runtime and Log domains, then listens for Runtime.consoleAPICalled, Runtime.exceptionThrown, and Log.entryAdded events, and returns an array of { level, text, url?, line?, source? }. This is a LIVE-WINDOW collector: it only captures events fired AFTER it attaches (plus the buffered history WebKit replays on enable), so triggering the logging from a SEPARATE tool call races the attach and is missed. To capture logs from an action, pass triggerJs (run inside the window). Default window: 5 000 ms. Maximum: 15 000 ms. Omit pageId to auto-pick the active page.

Input Schema

TableJSON Schema

Name	Required	Description
`udid`	Yes	iOS device UDID
`pageId`	No	CDP target id from ios_safari_list_pages. Omit it to use the page ios_safari_navigate last landed on (or, failing that, the first loaded page) — only pass it to target a DIFFERENT tab
`triggerJs`	No	JavaScript run INSIDE the collection window (after the listeners attach) so the logs it produces are captured race-free — e.g. "location.reload()" or "document.querySelector('#go').click()". Prefer this over triggering from a separate call.
`durationMs`	No	Collection window in milliseconds (default: 5000, max: 15000)
`platformVersion`	No	Ignored (kept for compatibility)

TDQS

A4.9/5.0

Behavior5/5

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

With no annotations, the description carries full responsibility for disclosing behavior. It states the tool is a LIVE-WINDOW collector, names the exact CDP events listened to (Runtime.consoleAPICalled, Runtime.exceptionThrown, Log.entryAdded), specifies the return array shape, and explains the race condition. It also provides window duration limits ('Default window: 5,000 ms. Maximum: 15,000 ms.')—all beyond basic 'collect logs' phrasing.

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 appropriately sized for a tool with 5 parameters and non-obvious timing behavior. Every sentence serves a purpose: purpose, mechanism, race warning, triggerJs recommendation, duration limits, pageId guidance. It is front-loaded with the core action and densely packs necessary caveats without fluff.

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?

Given the tool's complexity, the description covers all essential contexts: what it collects, the events behind it, the live-window semantics, how to trigger actions within the window, window bounds, and page targeting. The return format is stated explicitly. No output schema exists, but the description compensates thoroughly. There is no meaningful gap for an agent to misuse the tool.

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 value by explaining why triggerJs exists and how it avoids races, and clarifies the auto-pick pageId behavior. It also notes that platformVersion is ignored. This goes beyond the schema's field-level descriptions, justifying a 4. It doesn't fully redefine each parameter's syntax, but the added nuance is meaningful.

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 verb and resource: 'Collect console logs, exceptions, and log entries from a Safari page on an iOS device over a time window.' It clearly distinguishes itself from sibling tools like ios_safari_capture_network and session_console_logs by specifying platform (iOS Safari), resource (console), and the time-window behavior.

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?

The description gives explicit usage guidance: it warns that triggering logging from a separate tool call races the attach, and offers a precise alternative: 'To capture logs from an action, pass triggerJs (run inside the window).' It also tells users when to omit pageId ('Omit pageId to auto-pick the active page') and provides default/max duration values. This is a clear when/when-not/alternative pattern.

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?