Start recording a new scenario on a device. Automatically captures the initial app state and adds an appLaunch step. Returns a recordingId — pass it to flow_recording_action for each step, then flow_recording_save when done.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Name for the recording | |
| udid | Yes | Device UDID to record on | |
| category | No | Recording category (default: test) | |
| platform | No | Platform — auto-detected from connected devices if omitted |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It effectively discloses the key side-effect (automatically captures app state and adds an appLaunch step) and the return value (recordingId). It doesn't disclose failure states or required permissions, but the sequential handoff behavior is well explained. Slight deduction for not noting whether a recording must be cancelled/reverted if abandoned.
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?
Two sentences, zero waste. First sentence states purpose plus the two key side effects; the second explains the return value and sequential workflow. 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 stateful start tool with no output schema and no annotations, the description does well: it covers the return value, the automatic side effects, and the follow-up workflow. It slightly lacks guidance on edge cases (e.g., what if a recording is already in progress, or how to abandon a started recording, which flow_recording_cancel covers).
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 description coverage is 100%, so the schema already documents all 4 parameters (name, udid, category, platform). The description adds no parameter-specific semantics beyond what the schema provides. Per the baseline rule for high coverage, a 3 is appropriate.
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 uses a specific verb ('Start recording') plus the resource ('new scenario on a device'). It clearly states what the tool does, describes side effects (captures initial app state, adds appLaunch step), and distinguishes it from sibling flow_recording_* tools by defining its role as the entry point that returns a recordingId.
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 gives an explicit usage flow: call this first to get a recordingId, pass it to flow_recording_action for each step, then flow_recording_save when done. This is clear when-to-use guidance and explicitly names the sequential sibling tools, which is strong alternative/sequential context.
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.
