start_firmware_upgradeInstall a downloaded firmware package on an iKuai router. Set confirm to true to proceed; the router reboots and drops network connectivity for 1–2 minutes.
安装已下载的固件包 ⚠️⚠️ 路由器会重启断网 1-2 分钟
前提：本地已有固件文件（get_ota_info 的 fileinfo 非空）。
未下载固件时设备返回 2022 升级未成功，系统保持当前版本。
| Name | Required | Description | Default |
|---|---|---|---|
| confirm | No | 必须设为 True 才会执行 |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.0.1Input schema / properties / confirm / descriptionAdded value: +"必须设为 True 才会执行"v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden and does so well: it warns that the router reboots and the network drops for 1-2 minutes, states the prerequisite, and documents the concrete failure response (error 2022, system keeps current version). This is exactly the safety-impact context an agent needs before a disruptive write.
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 lines, front-loaded with the action and then the high-severity warning; the prerequisite and error-case details each earn their place and nothing is redundant.
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?
An output schema exists, so return values need not be explained. For a confirmed destructive operation with no annotations, the description supplies the risk, the prerequisite, and the failure mode — everything an agent needs to call this correctly.
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 the single 'confirm' parameter is already documented in the schema as requiring True to execute. The description adds no additional meaning about that flag, so the baseline 3 for high-coverage schemas applies.
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 states a specific verb+object ('安装已下载的固件包' / install the downloaded firmware package), clearly distinguishing it from sibling read/maintenance tools such as get_firmware_version, check_firmware_update, clean_firmware_files, and the AP-scoped upgrade_ap_firmware. An agent can identify the operation without opening the schema.
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?
It explicitly states the precondition for use — a firmware file must already exist locally, verified via get_ota_info's fileinfo being non-empty — and names the failure case when that precondition is unmet. It does not, however, point to the download/check sibling or describe what to do instead when the firmware is absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.