Stop the active native packet capture on an iOS device and return the capture as a pcapng. Small captures (<1 MB) are returned inline as base64; larger ones are written to a .pcapng file on the RDS host and the path is returned. Open the pcapng in Wireshark.
| Name | Required | Description | Default |
|---|---|---|---|
| udid | Yes | iOS device UDID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure and does well: it explains output behavior (small captures inline as base64, larger written to .pcapng on RDS host with path returned) and instructs opening in Wireshark. This is meaningful behavioral context beyond what annotations would provide.
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 compact and efficient, packing useful functional detail (output format handling, size threshold, return mechanism) into 3 sentences without redundancy. It's front-loaded with the core action and adds the valuable return-format detail.
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 tool with high schema coverage and no output schema, the description is fairly complete. It addresses the main uncertainty—how the capture result is returned (inline vs. file path with size threshold)—which is the key behavioral detail. It could note rounding down to the thousandth, but that's minor.
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% with a single udid parameter that is clearly documented ('iOS device UDID'). The description adds no additional parameter semantics, but with high schema coverage, baseline 3 is appropriate. The description does reference the device context implicitly.
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 stops an active iOS packet capture and returns the capture as pcapng. It uses a specific verb (stop) with a clear resource (native packet capture on iOS device) and distinguishes itself from ios_pcap_start and ios_pcap_status siblings.
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 usage (stop an active capture) but doesn't explicitly state prerequisites like having started a capture with ios_pcap_start first, or when to prefer this over other capture tools like ios_mitm_stop. Context is implied by the name and sibling relationships rather than stated.
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.
