DESKTOP browser on the testing grid — NOT a phone or tablet. Opens a page and navigates to a URL, returning a pageId that every other web_* tool takes. To drive the browser ON A REAL DEVICE instead, use the webpage_* tools, which take a udid.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to navigate to | |
| browser | No | Browser to use: chrome | firefox | safari (default: chrome) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosure. It reveals that this is a desktop browser (not mobile), returns a pageId, and is the entry point for web_* tools. However, it does not disclose any failure behavior, timeouts, or whether navigation is synchronous, leaving some behavioral ambiguity.
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 two sentences, front-loaded with the most critical context (desktop browser, NOT mobile), and every sentence earns its place. It efficiently conveys purpose, return value, and an explicit alternative without redundancy.
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?
The tool is simple and the description covers its core behavior, return value, and usage context. It even provides a clear alternative for real-device automation. Given no output schema, the description adequately explains what to expect (a pageId). Minor gaps like error cases are not critical for this basic navigation 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 description coverage is 100%, and the schema already documents the 'url' and 'browser' parameters with descriptions. The description adds no additional parameter-level semantics beyond confirming that it navigates to a URL. Per rubric, baseline 3 is appropriate when schema covers all parameters.
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 the tool's function: it opens a page and navigates to a URL, returning a pageId used by other web_* tools. It also explicitly distinguishes itself from the webpage_* tools by noting it operates on a desktop browser, not a phone or tablet.
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 explicit guidance on when to use this tool versus alternatives: it states that for real-device browser automation, the webpage_* tools should be used instead. It also implies a workflow by mentioning the returned pageId is consumed by every other web_* tool, making it the entry point for browser automation on the desktop grid.
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.
