Compact replay summary for analysis. Returns replay metadata (totals, passed/failed/skipped counts) + one row per step with status, action, duration, diff scores, and a short error excerpt. Always small — call this first when analyzing a replay, then use flow_replay_step for full per-step detail.
| Name | Required | Description | Default |
|---|---|---|---|
| replayId | Yes | Replay ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It transparently discloses the compact/small footprint ('Always small') and describes what data is included (totals, per-step rows with status/action/duration/diff scores, error excerpt). It doesn't mention pagination limits or truncation behavior for error excerpts, but the scope of returned data is well described.
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 two sentences and every sentence earns its place. The first sentence states purpose and output contents, the second gives explicit usage guidance and names the alternative tool. Zero filler words.
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?
Despite no output schema, the description enumerates the exact return contents (totals, counts, one row per step with status/action/duration/diff scores/error excerpt). The 'call this first, then flow_replay_step for detail' workflow guidance makes this fully complete for decision-making. Single simple parameter, clear scope.
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 coverage is 100% for the single replayId parameter, so the schema already documents it. The description goes beyond by explaining what the parameter is used for conceptually (analyzing a replay summary). However, it doesn't add type or format details for replayId beyond 'Replay ID' in the schema. Baseline of 3 with slight enhancement due to the context around the parameter's role.
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 this is a 'Compact replay summary for analysis' that returns replay metadata plus per-step details (status, action, duration, diff scores, error excerpt). It explicitly distinguishes from flow_replay_step by noting the summary is 'Always small' and is the first thing to call. This clearly separates it from its sibling flow_replay_step.
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?
Explicit guidance is provided: 'call this first when analyzing a replay, then use flow_replay_step for full per-step detail.' This is an explicit usage instruction that names the alternative tool and establishes the correct call order, making it very clear when to use this tool versus the sibling.
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.
