Robot Actions — Remote Device Control

android_devtools_evaluate

Evaluate a JavaScript expression in the context of a page running on the device via CDP. Enables Runtime, then calls Runtime.evaluate. Returns the result value, any exception details, and pageId/pageUrl identifying the tab it actually ran on — check those if a result looks like it came from the wrong page. Omit pageId to auto-select the active tab (after a navigate, that is the tab the navigate landed on).

Input Schema

TableJSON Schema

Name	Required	Description
`udid`	Yes	Device serial number (UDID)
`pageId`	No	Target page id from android_devtools_list_pages (auto-picked when omitted)
`socket`	No	Abstract unix socket name (default: chrome_devtools_remote)
`expression`	Yes	JavaScript expression to evaluate
`awaitPromise`	No	Whether to await a returned Promise (default: true)
`returnByValue`	No	Return the result as a serializable value (default: true)

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the full burden. It discloses that enabling Runtime is a side effect, that results include pageId/pageUrl to catch wrong-page execution, and that omitting pageId auto-selects the active tab with a navigation-specific behavior. This is rich behavioral context, though it doesn't address potential error conditions or side effects of the JS execution itself.

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 three sentences, front-loaded with the core purpose, and each sentence adds value—purpose, return behavior, and pageId auto-selection. No fluff or redundancy.

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?

There is no output schema, but the description covers the key return fields (result, exception details, pageId/pageUrl) and the wrong-page caveat. It could be more complete with error cases or prerequisites, but for a 6-param tool with 100% schema coverage, it provides enough context for an agent to use it correctly.

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 the baseline is 3. The description adds minor extra context for pageId (auto-select after navigate), but does not add meaningful semantics for other parameters like awaitPromise or returnByValue beyond what the schema already states.

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 it evaluates a JavaScript expression in the context of a page on the device via CDP, with a specific verb and resource. It distinguishes itself from sibling tools by mentioning the CDP mechanism, the Runtime enablement, and the return of pageId/pageUrl to identify the actual target tab.

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?

It provides clear context: use this to evaluate JS in a page on an Android device, and it explains how pageId selection works (auto-selecting the active tab, especially after a navigate). It does not explicitly mention alternatives, but the context and name make the intended use clear.

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?