Get a LIVE video-stream link for an iOS device that a human can open in a browser to watch the screen in real time (unlike ios_screenshot, which is one frame). Returns a short-lived, single-device viewer URL — open it directly; no login or session required for ~5 minutes. Use this to let a person supervise what the agent is doing on the device.
| Name | Required | Description | Default |
|---|---|---|---|
| udid | Yes | iOS device UDID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. Despite that, it discloses key behavioral traits: the link is short-lived (~5 minutes), requires no login/session, is single-device, is meant for a human to open in a browser, and is LIVE (realtime vs one-frame). It doesn't mention rate limits, whether the stream persists after another tool call, or how to terminate the stream, leaving some gaps in a no-annotation context.
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 three sentences, all substantive: purpose, output characteristics, and usage guidance. There is zero filler or redundancy. Every sentence earns its place, with the distinguishing sibling comparison embedded efficiently.
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 single-parameter tool with 100% schema coverage, full purpose clarity, and explicit usage guidance, the description is essentially complete. It clearly articulates what the agent gets back, how it's used (human opens in browser), its temporal scope (~5 min), and its access model (no login). It omits potential details like stream termination or concurrent stream limits, but these are not critical for a minimal-parameter, well-covered tool.
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?
There is only one parameter (udid) which is fully documented in the schema (100% coverage), so baseline is 3. The description references the device context ('an iOS device') but doesn't add additional semantics beyond the schema's 'iOS device UDID'. The single, well-documented parameter means minimal description burden, so a slightly above-baseline score is reasonable for the clarity provided.
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 clearly states specific verb+resource: 'Get a LIVE video-stream link for an iOS device.' It explicitly distinguishes from the sibling ios_screenshot tool ('unlike ios_screenshot, which is one frame') and states what the result is ('short-lived, single-device viewer URL'). This is a precise, differentiating purpose statement.
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 explicitly states when to use it ('Use this to let a person supervise what the agent is doing on the device') and distinguishes it from the alternative ios_screenshot by noting the one-frame vs live contrast. The mention of 'open it directly; no login or session required for ~5 minutes' also sets clear expectations about how the link is consumed.
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.
