Stop a performance recording started with ios_performance_record_start and return the full time-series + a per-process summary (avg/peak CPU, peak memory).
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes | Session id from ios_performance_record_start |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses that it stops a recording and returns data but does not describe side effects (what happens to the recording buffer after stop, whether data is cleared, whether another start is required for a new session, or what happens if the session doesn't exist). For a termination tool this is adequate but minimal.
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?
A single sentence that conveys the action, the dependency, and the return value with zero waste. No redundancy with the schema. Front-loaded with the action verb.
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 pairs cleanly with its start companion, and there is no output schema, so the description helpfully enumerates the return contents (time-series, per-process avg/peak CPU, peak memory). However, it doesn't cover error cases (unknown/invalid sessionId), session lifecycle implications (can it be stopped twice?), or whether data is retained after stopping. Adequate for a simple 1-param paired tool but not comprehensive.
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% — the single sessionId parameter is documented in the schema as 'Session id from ios_performance_record_start'. The description also reinforces the session's provenance by naming the source tool. With only one parameter fully described in the schema, the description adds marginal but non-zero value (clarifying the output format). Baseline 3 adjusted slightly upward.
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 (Stop a performance recording) and the resource (one started with ios_performance_record_start), and specifies the return value (full time-series + per-process summary with avg/peak CPU and peak memory). This is specific enough to differentiate from the start companion or the snapshot sibling, though it doesn't explicitly name an alternative tool.
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 the prerequisite companion tool (ios_performance_record_start), which is the key usage context — it only makes sense to call this after starting a recording. It does not explicitly say 'do not use android_performance_record_stop' for iOS or distinguish from ios_performance_snapshot, but the pairing with the start tool provides clear enough context for when to use it.
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.
