Replace the entire memory file for the calling user. USE SPARINGLY — append is the safer primary. Only call replace when memory has drifted wrong, accumulated stale entries, or the user asks for a clean rewrite. Cap: 10240 bytes; over-cap calls return 413.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | Full memory content (Markdown). Pass empty string to clear. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It does disclose the 10240-byte cap with the 413 error behavior, which is valuable. However, it doesn't disclose side effects beyond the implied whole-file overwrite, nor what happens to the existing memory content (though 'replace the entire memory file' implies full overwrite). The risk framing ('USE SPARINGLY') adds context but the description is somewhat thin on full behavioral detail.
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 short sentences, all earning their place: purpose, usage guidance, and the technical cap. The 'USE SPARINGLY' emphasis is front-loaded in the first line. Efficient and readable; only minor inefficiency is the mild redundancy between 'USE SPARINGLY' and the guidance that follows.
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 tool with no output schema and simple semantics, the description is fairly complete. It covers the purpose, the when/when-not (append as alternative), the cap behavior with error code, and the clear-option. The main gap is that it doesn't explain the return value, but for a write-only replace tool with no output schema, this is acceptable.
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 the 'content' parameter. The description adds modest value by noting 'Pass empty string to clear,' which is useful beyond what the schema states ('Full memory content (Markdown)'). This matches the baseline-3 scenario where the schema does heavy lifting with a small description bonus.
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 purpose: "Replace the entire memory file for the calling user." It uses a specific verb (replace) with a specific resource (memory file). It doesn't heavily distinguish from siblings beyond implying it's the 'less safe' counterpart to append, but the scope ('entire memory file') is precise.
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 explicitly guides when to use this tool: "USE SPARINGLY — append is the safer primary." It names the alternative (append) and the specific conditions for using replace: 'memory has drifted wrong, accumulated stale entries, or the user asks for a clean rewrite.' This is excellent when/when-not guidance.
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.
