Delete a finished iOS recording mp4 from disk. Pass the httpPath returned by ios_record_stop. Idempotent — deleting a non-existent file is not an error. Refuses to delete recordings that are still being written (call ios_record_stop first).
| Name | Required | Description | Default |
|---|---|---|---|
| httpPath | Yes | httpPath returned by ios_record_stop (e.g. /recordings/rec-ios-<uuid>.mp4) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and does an excellent job. It discloses idempotency (deleting non-existent file is not an error), the refusal to delete in-progress recordings, and the prerequisite condition. This is exactly the kind of behavioral context an agent needs beyond the schema.
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 sentences, each earning its place: what it deletes, the idempotency guarantee, and the in-progress refusal. No wasted words, front-loaded with the core action.
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 delete operation with a well-documented schema and strong description, this is complete. It covers the safety-relevant edge cases (non-existent file, in-progress recording) and the input provenance. No output schema needed for a delete returning void/nothing.
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?
The schema already documents the httpPath parameter with 100% coverage including a concrete example pattern (/recordings/rec-ios-<uuid>.mp4). The description adds the source of that value (returned by ios_record_stop), which reinforces how to acquire it. Both schema and description work together well.
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 (delete), resource (finished iOS recording mp4), and even specifies the exact input parameter (httpPath from ios_record_stop). It fully distinguishes this from ios_record_start/ios_record_stop siblings which manage recordings rather than delete them.
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 clearly states what to pass (httpPath) and where to get it from (ios_record_stop). It gives a clear prerequisite ('Refuses to delete recordings that are still being written, call ios_record_stop first'). It doesn't explicitly name alternative tools for when not to use it, but the cleanup-specific purpose is clear enough that exclusions are largely self-evident.
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.
