Return the screenshot for one step of a replay as an image you can view directly. kind="recorded" is what was captured during recording; "live" is what the device showed during replay; "diff" is the visual diff overlay. Use selectively — not every step needs visual inspection.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | Which image to load | |
| replayId | Yes | Replay ID | |
| stepIndex | Yes | Step index (1-based) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It states the output is 'an image you can view directly' which is useful. However, it doesn't disclose potential cost or performance implications of fetching screenshots, whether invalid kind values error out, or what the diff overload actually means visually. The 'visual diff overlay' explanation is good context, but there's room for more behavioral disclosure.
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 concise sentences, zero waste. Front-loaded with the core purpose, then explains kind variants, then adds a usage-timing note. Every sentence earns its place.
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 screenshot-fetching tool with 100% schema coverage on 3 simple parameters and no output schema, the description is largely complete. It covers the purpose, the kind semantics, and even advises on selective usage. The only gap is minor — no mention of what happens with out-of-range stepIndex or error behavior — but for this tool's simplicity, it's adequate.
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%, so the schema already documents all three parameters (kind, replayId, stepIndex). The description adds meaning by explaining the three kind enum values and the '1-based' step index is already in the schema. The description contributes marginal value by clarifying the recorded/live/diff semantics beyond the schema's terse 'Which image to load'.
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 what the tool does: 'Return the screenshot for one step of a replay as an image you can view directly.' It's specific about the verb (return/view), the resource (screenshot for one step of a replay), and the output format (image). It differentiates the three kind values and is distinct from the siblings like flow_replay_step and flow_replay_summary.
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 when to use it ('Use selectively — not every step needs visual inspection') and distinguishes the three kind options (recorded vs live vs diff). However, it doesn't explicitly name sibling alternatives or state when NOT to use this tool in favor of other screenshot tools like device_screenshot or session_screenshot, though the replay-scoping makes this fairly implicit.
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.
