Set files on a file input in the DESKTOP grid browser (by pageId). Paths are read on the RDS host, not your machine. NOT a device — there is no webpage_upload_file; the device equivalent is ios_safari_set_input_files (by udid).
| Name | Required | Description | Default |
|---|---|---|---|
| paths | Yes | Absolute file paths on the RDS host | |
| pageId | Yes | Page ID from web_navigate | |
| selector | Yes | CSS selector of the <input type=file> |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It discloses the non-obvious trait that paths are read on the RDS host rather than the caller's machine, and it clarifies the browser/device boundary. It does not describe return behavior or failure modes, but for a simple file-input setter the core side-effect expectations are communicated.
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 short sentences, each with a distinct purpose: what the tool does, where paths are read, and what it is not. The important scoping caveat appears early, and device alternatives are given without padding.
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 tool with only three fully documented required parameters and no output schema, the description plus schema is nearly sufficient. The main missing piece is behavior on error (e.g., nonexistent host paths or invalid selectors), but an agent can invoke the tool correctly with the information given.
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 baseline is 3. The description adds the RDS-host warning, but that is already reflected in the paths schema ('Absolute file paths on the RDS host'). No parameter-level meaning beyond the schema is provided, though none is urgently needed.
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 opens with a specific action and resource ('Set files on a file input') and scopes it to the DESKTOP grid browser keyed by pageId. It explicitly marks what the tool is not (a device operation) and names sibling alternatives, so an agent can differentiate it from ios_safari_set_input_files and web_upload_file.
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?
States when it applies (DESKTOP grid browser, pageId) and when not ('NOT a device'), with an explicit alternative (ios_safari_set_input_files by udid). The RDS-host caveat also prevents the common mistake of using local paths. This is explicit when/when-not 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.
