FPS / jank stats for a package via dumpsys gfxinfo (total/janky frames, jank %, frame-time percentiles, missed vsyncs).
| Name | Required | Description | Default |
|---|---|---|---|
| pkg | Yes | App package name, e.g. com.android.settings | |
| serial | Yes | Android device serial (from `device_list`) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly states this is a read operation that extracts FPS/jank data via dumpsys gfxinfo and lists the metrics returned (total/janky frames, jank %, frame-time percentiles, missed vsyncs). However, it doesn't disclose whether metrics are cumulative or session-based, whether a running app is required, or if the app needs to be foregrounded. For a no-annotation tool, the description gives a reasonable but imperfect behavioral profile.
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?
Single sentence, dense but clear, listing the data source and all metric categories. Every element earns its place with no filler.
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 has only 2 parameters fully documented in the schema (100% coverage), no output schema, and no annotations. The description tells the agent what stats it produces from a specific command, which is sufficient for a query tool. It could mention prerequisites (e.g., app must be installed/running) but overall covers the essential context for a metrics-read 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% — both serial and pkg come with descriptions referencing device_list for serial and giving an example package name. The description adds the metric details but doesn't expand parameter semantics further. Baseline 3 is appropriate given 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 states a specific verb+resource ('FPS / jank stats for a package via dumpsys gfxinfo') and enumerates the exact metrics produced. It differentiates from siblings like android_app_launch_time and ios_fps by naming the command source and metric set. Clear purpose that distinguishes it effectively.
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?
No explicit guidance on when to use this tool vs android_performance_snapshot, android_performance_record_start/stop, or ios_fps. It implicitly conveys it's for FPS/jank measurement, which suggests use cases, but it doesn't name alternatives or exclusion criteria. Adequate but not explicit.
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.
