List files and directories at a path on the device. Uses the device file-sync protocol (no shell roundtrip). Returns { ok, remotePath, count, entries: [{ name, isDir, size, modTime }] }. Common roots: /sdcard/ (user storage), /sdcard/Download, /sdcard/DCIM. Symlinks are resolved one level.
| Name | Required | Description | Default |
|---|---|---|---|
| udid | Yes | Device serial number (UDID) | |
| remotePath | Yes | Absolute path on the device, e.g. /sdcard/Download |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the return format ({ok, remotePath, count, entries}), the protocol used (file-sync, no shell roundtrip), and an edge behavior (symlinks resolved one level). This is solid behavioral disclosure for a read-only listing operation, though it doesn't detail error cases or permissions.
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?
Four sentences, zero wasted words. Every sentence adds value: what it does, protocol note, return shape, and common roots. Front-loaded with the core purpose and immediately follows with actionable details.
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 fairly simple two-parameter read-only listing tool, this description is well-rounded. It documents the return structure inline, gives practical path examples, and notes the symlink behavior. It lacks an explicit output schema but compensates by documenting the return shape in prose. Error handling and permission requirements are not addressed, but breadth is appropriately capped for a low-complexity 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?
Schema coverage is 100% with both parameters (udid, remotePath) documented in the schema. The description adds value by clarifying common root paths and showing example values (/sdcard/Download), plus the entry fields (name, isDir, size, modTime) which enrich what parameters would return. This slightly exceeds the baseline 3 for full schema coverage.
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 'List files and directories at a path on the device', a specific verb+resource combo. It distinguishes from sibling tools like device_file_pull and device_file_push by naming the file-sync protocol (no shell roundtrip) which separates it from device_shell. It also documents the exact return shape.
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 clear usage context by listing common roots (/sdcard/, /sdcard/Download, /sdcard/DCIM) which helps an agent know typical paths to use. However, it doesn't explicitly state when NOT to use this tool or name alternatives like device_shell, though the file-sync protocol note implies the distinction.
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.
