subnet_calculatorCalculate subnet network, broadcast, and usable host range from an IP address and optional mask or prefix, using local computation instead of router queries.
子网换算工具（本地计算，不依赖设备）
设备侧没有 subnet func_name（实测 4.0.313 返回 1003），
因此该工具在本地完成换算。
| Name | Required | Description | Default |
|---|---|---|---|
| ip | Yes | IP 地址，如 "192.168.9.101" | |
| mask | No | 子网掩码 "255.255.255.0" 或前缀长度 "24" | 255.255.255.0 |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.0.1Input schema / properties / ip / descriptionPrevious value: -"IP 地址"New value: +"IP 地址，如 \"192.168.9.101\""Input schema / properties / mask / defaultAdded value: +"255.255.255.0"Input schema / properties / mask / descriptionPrevious value: -"子网掩码"New value: +"子网掩码 \"255.255.255.0\" 或前缀长度 \"24\""Input schema / requiredPrevious value: -[
- "ip",
- "mask"
-]New value: +[
+ "ip"
+]v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint=true already covering the safety profile, the description adds real behavioral context: computation happens locally and does not depend on the device, and it explains why. That tells the agent the result is deterministic and unaffected by device state, firmware support, or connectivity. It does not discuss output format, which is acceptable given an output schema exists.
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?
Two short lines, purpose first, rationale second — nothing padding. The firmware/error-code detail ('实测 4.0.313 返回 1003') is the weakest part; it justifies why the tool exists but is trivia the agent does not need to call it, though it is brief enough not to hurt.
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?
A two-parameter, no-side-effect utility with a full schema, an output schema, and a read-only annotation needs little prose, and the description supplies the one non-obvious fact: this is a local calculator, not a device query. Only the narrowed coverage of what exactly is computed keeps it from being 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%: `ip` is documented with an example and `mask` with both dotted-decimal and prefix-length forms and a default. The description adds nothing about the parameters, so the baseline 3 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 names a specific verb and resource (子网换算/subnet conversion) and adds a scope qualifier (本地计算，不依赖设备), which is enough to distinguish it from the surrounding router-configuration siblings. It stops short of saying exactly what it converts (IP+mask into network/broadcast/range), so an agent must infer the output from the tool name plus 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?
Usage is only implied: the tool is local because the device exposes no `subnet` func_name, so an agent that would otherwise look for a device-side subnet call is steered here. There is no explicit 'use this when / don't use this when' and no named alternative, but the sibling list contains no competing calculator, so the risk of misselection is low.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.