List crash reports on an iOS device with aggregate analytics (total, per-app, per exception type, per-day timeline). Telemetry and in-house automation processes are excluded. Use ios_crash_detail with a returned crash id for the full log. No automation session required.
| Name | Required | Description | Default |
|---|---|---|---|
| udid | Yes | iOS device UDID |
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 discloses scope exclusions (telemetry/in-house automation), the no-session-required trait, and the output shape (aggregate analytics). It doesn't fully describe edge cases like empty device or formatting, but the observable behavior coverage is solid for a read-only list tool.
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 tight sentences, zero filler. Every sentence earns its place: scope+output (sentence 1), exclusions (sentence 2), pointer to sibling + prerequisite (sentence 3). Front-loaded with the core purpose.
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 aggregation list tool with one parameter, 100% schema coverage, and no output schema, the description is complete: it states scope, exclusions, the alternative for detail, and session requirement. Nothing material is left ambiguous for the agent's selection and invocation.
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 parameter (udid) described as 'iOS device UDID.' The description adds value by confirming udid refers to the iOS device for which crashes are listed and not needing automation session context. With only one self-evident parameter, the description complements rather than repeats the schema adequately.
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 verb (List) and resource (crash reports on iOS device) plus the specific aggregation dimensions (total, per-app, per exception type, per-day timeline). It distinguishes from siblings like ios_crash_detail (full log) and ios_crash_list, and even names the alternative tool explicitly.
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?
Explicitly directs the agent to use ios_crash_detail with a returned crash id for full logs, names the alternative tool, and clarifies that telemetry/in-house automation processes are excluded. Notably states 'No automation session required,' which is a concrete usage prerequisite that helps the agent decide when to invoke this tool.
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.
