Send strings or binary data to a WebSocket server from the active EDA window, enabling real-time communication with external services.
sys_WebSocket.send(id: string, data: string | Blob | BufferSource, extensionUuid?: string) -> void
向 WebSocket 服务器发送数据
remarks: 注意：本接口需要使用者启用扩展的外部交互权限，如若未启用将始终 throw Error
| Name | Required | Description | Default |
|---|---|---|---|
| args | No | 按官方签名顺序排列的JSON参数数组 | |
| windowId | No | 目标EDA窗口ID；省略时使用当前活动窗口 |
Changes observed during successful MCP inspections.
v2.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses a critical failure mode (throws Error without permission), which is valuable. It also conveys the void return and accepted data types via the signature. This exceeds minimal disclosure, though it could add details about connection state requirements or side effects.
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 compact: a signature line and two short sentences, with the critical permission warning placed right after the action. Every sentence adds value, and the structure is front-loaded with the most important information.
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 WebSocket send operation with no annotations, the description covers the essential purpose, signature, and a key prerequisite. It omits details like connection status prerequisites or error handling beyond throwing, but the void return type is indicated)Skip. Overall, it provides enough for an agent to invoke the call correctly in most cases.
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?
The description includes the full signature with parameter names, types, and optionality (id, data, extensionUuid?), which adds meaning beyond the schema's generic 'args' array. The schema only lists 'args' and 'windowId' with minimal descriptions, so the signature is essential for understanding correct parameter ordering and types. This compensates well for the schema's sparse detail.
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 the action clearly: '向 WebSocket 服务器发送数据' (send data to WebSocket server), and provides the full function signature. It differentiates from sibling WebSocket tools like close and register by naming the send operation explicitly, though it does not name those siblings directly.
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 gives a key usage condition: the extension must have external interaction permission enabled, otherwise the call always throws an Error. However, it does not explicitly describe when to use this tool versus alternatives (e.g., register/close), nor does it provide exclusions. The permission prerequisite is useful but not a full routing guide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.