Snapshot per-process CPU %% and memory for a physical iOS device. Returns the top processes by CPU, or just one app when bundleId is given. No automation session required.
| Name | Required | Description | Default |
|---|---|---|---|
| topN | No | Limit to the top-N processes by CPU (default 15) | |
| udid | Yes | iOS device UDID | |
| bundleId | No | Focus a single app by bundle id (or app/process name), e.g. com.apple.mobilesafari |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. It clarifies 'physical device' (not simulator) and 'No automation session required' — useful non-obvious context. However, it doesn't disclose metrics granularity, sampling duration, or whether this is a snapshot vs monitoring (the name implies snapshot). The phrase 'top processes by CPU' hints at return content but not in detail.
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 concise sentences with zero wasted words. The description front-loads the core purpose, then adds scope detail and the key behavioral note about no session required. Efficient and appropriately sized.
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 read-only snapshot tool with full schema coverage and no output schema, the description is largely complete: purpose, target device, scoping options are all present. The only gap is not mentioning return format (e.g., does it return a list with % labels), but the description's 'Returns the top processes by CPU' partially addresses this. A snapshot tool with this clarity is adequate.
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 each parameter documented (topN limit, udid, bundleId). The description adds marginal value by explaining that bundleId also accepts 'app/process name', which extends beyond the schema's 'bundle id' phrasing — this is genuinely useful. Otherwise the description mostly restates what the schema already provides.
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 states a specific verb+resource ('Snapshot per-process CPU and memory for a physical iOS device') and clarifies scope (top processes by CPU or single app by bundleId). It distinguishes from generic device snapshots but doesn't explicitly contrast with the sibling 'android_performance_snapshot' or 'ios_ps'.
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 implies physical device usage ('No automation session required') and when bundleId focuses a single app. However, it doesn't explicitly name alternatives like ios_ps or ios_performance_record_start/stop, nor clarify when this vs those should be preferred.
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.
