Crash / ANR / native-crash analytics from DropBoxManager (total, per-process, per-type, per-day timeline). Use android_crash_detail for one entry.
| Name | Required | Description | Default |
|---|---|---|---|
| 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 full burden. The description tells us the tool returns analytics data structured as totals/process/type/day but doesn't disclose side effects (likely none), return format, or what happens if no dropbox entries exist. For a read-only analytics tool, this is reasonably adequate but thin.
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?
Two sentences, zero waste. Front-loaded with the core purpose and data sources, closes with the sibling pointer. Every word earns its place.
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 single-parameter aggregate analytics tool with no output schema, the description covers the purpose, data source, aggregation dimensions, and sibling distinction. It doesn't need to explain return values in depth since there's no output schema and the value proposition is clear. Could add what 'no crashes' looks like, but not critical for a stats 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 a single 'serial' parameter already documented as 'Android device serial (from device_list)'. The description adds context by clarifying the data source (DropBoxManager) and output granularity, which enriches the single parameter's purpose beyond the schema. With only 1 parameter and full schema coverage, baseline is 3; the DropBoxManager sourcing detail justifies a slight bump.
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 this aggregates crash/ANR/native-crash analytics with specific breakdowns (total, per-process, per-type, per-day timeline). It distinguishes itself explicitly from android_crash_detail, the sibling for individual entries. Very specific verb+resource+scope.
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 names android_crash_detail as the alternative for individual entries, giving clear 'when vs when-not' guidance. However, it doesn't describe when to prefer this over ios_crash_analytics or specify any filter or selection context beyond device serial.
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.
