List every test step that references a given component (fragment) via a live COMPONENT_REF. Backs the deletion guard: a component in use cannot be deleted. Returns the referencing recording id, display id, name, and step index. The component must be a fragment owned by the authenticated user.
| Name | Required | Description | Default |
|---|---|---|---|
| componentId | Yes | Component (fragment) recording ID to look up usage for |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears the full burden of behavioral disclosure. It is clearly a read operation (lists references), discloses the ownership requirement, and specifies what data is returned. While it doesn't discuss errors (e.g., component not found, unowned component), the description covers the core behavioral contract reasonably well for a read-only lookup 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?
The description is dense and efficient — three sentences that cover purpose, return values, and a prerequisite without fluff. It could arguably front-load better by leading with the specific action before any context, but it does open with 'List every test step...' which is the strongest possible lead. No wasted sentences.
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?
Given this is a simple read-only lookup with one parameter, full schema coverage, and no output schema, the description provides what's needed: the exact return fields (recording id, display id, name, step index), the reference type (COMPONENT_REF), and a usage context (deletion guard). A minor gap is the absence of error-path detail, but for a low-complexity tool this is nearly complete.
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%, and there's only a single parameter (componentId) which the schema fully documents as 'Component (fragment) recording ID to look up usage for'. The description reinforces that this is the fragment to look up. With full schema coverage and a single, self-explanatory parameter, the description adds little beyond the schema, so the baseline of 3 is appropriate.
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 begins with a specific verb+resource: 'List every test step that references a given component (fragment) via a live COMPONENT_REF.' It clearly distinguishes itself by explaining it backs a deletion guard and returns specific fields (recording id, display id, name, step index). This is a well-scoped purpose that stands apart from its 170+ siblings by its specific domain (flow component references for deletion safety).
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 explains the deletion-guard context ('a component in use cannot be deleted') which tells the agent when this is relevant, and states a clear ownership prerequisite ('must be a fragment owned by the authenticated user'). It doesn't name explicit alternative tools to use vs. not, but the deletion-guard framing provides clear contextual guidance for why and when to invoke this.
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.
