Stop a screen recording started by device_record_start. Closes the remux pipeline cleanly so the mp4 has a valid moov atom. Returns hostPath (already on the server host), sizeBytes, durationMs, and the negotiated codec/resolution.
| Name | Required | Description | Default |
|---|---|---|---|
| recordingId | Yes | recordingId returned by device_record_start |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the key behavioral detail that this is a side-effectful operation (closes the remux pipeline) and explains why it matters ('so the mp4 has a valid moov atom'). It also discloses it returns an on-server file path rather than downloading content. This is meaningful beyond the bare 'stop recording' phrasing.
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?
Three sentences, all earning their place: purpose, critical behavioral note about the moov atom, and the return-value contract. No filler or fluff. It could arguably be slightly more compact, but every clause adds information for an agent deciding whether and how to invoke it.
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 no output schema and no annotations, the description covers the essentials: what it does, its prerequisite, its clean-closure behavior, and what it returns. It doesn't describe error cases (what happens if recordingId is invalid or recording already stopped), but for a companion stop tool this is adequate given the return contract is well spelled out.
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% and the single parameter recordingId is described as 'recordingId returned by device_record_start' in the schema itself. The description reinforces this by naming the source tool and the return contract (hostPath, sizeBytes, durationMs, codec/resolution). Since there's only one param with full schema coverage, the description adds minimal extra beyond linking it to the return value.
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+resource: 'Stop a screen recording started by device_record_start.' It names the paired tool explicitly, distinguishes from siblings like ios_record_stop and android_performance_record_stop, and references the remux pipeline which identifies it as the Android/device screen recording counterpart. This clearly differentiates from flow_recording_stop and performance recordings.
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 implicitly establishes usage context by referencing device_record_start as its prerequisite pairing, which tells the agent when to use this tool (after starting a recording). It doesn't explicitly state when-not-to-use or name alternatives like ios_record_stop, but the pairing is self-explanatory enough given the sibling list contains similar record-stop tools.
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.
