Run JavaScript in the DESKTOP grid browser page (by pageId) and return the result. Not a device — for a phone or tablet use android_devtools_evaluate or ios_safari_evaluate (by udid).
| Name | Required | Description | Default |
|---|---|---|---|
| pageId | Yes | Page ID from web_navigate | |
| script | Yes | JavaScript expression to evaluate (e.g. "document.title" or "() => window.location.href") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It clarifies the desktop grid browser context but does not mention that running arbitrary JavaScript may have side effects on the page, nor does it describe error handling or result serialization. This leaves some behavioral ambiguity for a powerful evaluate tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core action and resource, followed by a compact exclusion. No fluff or repetition; every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 2-parameter tool with no output schema, the description captures the core purpose, platform scope, and alternative tools. It does not explain return value structure or error behavior, but those are secondary for an evaluate tool and the schema covers the script syntax. Overall, it is largely complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters described (pageId from web_navigate, script with examples). The description adds only the 'DESKTOP grid browser' context for pageId, which is marginal. Baseline 3 is appropriate since the schema already documents parameter meaning and syntax.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states 'Run JavaScript in the DESKTOP grid browser page (by pageId) and return the result.' This clearly identifies the action, resource, and output. It also distinguishes from siblings by stating 'Not a device' and naming the alternate mobile tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit exclusions: 'Not a device — for a phone or tablet use android_devtools_evaluate or ios_safari_evaluate (by udid).' It tells when not to use this tool and names the exact alternatives, which is ideal usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
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.
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).
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.
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.
