Skip to main content
Glama
aliyun
by aliyun

CreateNode

Create data development nodes in DataWorks workspaces to automate data processing workflows with configurable scheduling, dependencies, and execution parameters.

Instructions

创建数据开发节点 *This Tool has a 'MCP Resource',please request CreateNode(MCP Resource) to get more examples for using this tool.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ProjectIdNoDataWorks工作空间的ID
SceneYes节点创建的场景,决定节点创建在手动节点区域还是数据开发区域。DataworksManualWorkflow只在填写了ContainerId且Container为手动工作流时才能使用。可选值:- DATAWORKS_PROJECT 项目目录- DATAWORKS_MANUAL_WORKFLOW 手动工作流- DATAWORKS_MANUAL_TASK 手动任务
SpecYes{ "title": "CycleWorkflow Schema", "description": "定义周期性工作流及其节点配置的JSON Schema", "type": "object", "required": ["version", "kind", "spec"], "properties": { "version": { "type": "string", "const": "1.1.0", "description": "Schema版本号,当前固定值1.1.0" }, "kind": { "type": "string", "enum": ["Workflow", "Node"], "description": "资源类型,标识工作流的具体类型" }, "spec": { "type": "object", "description": "工作流核心配置规范", "required": ["nodes"], "properties": { "nodes": { "type": "array", "description": "工作流节点列表", "items": { "type": "object", "required": ["name", "script"], "properties": { "recurrence": { "type": "string", "enum": ["Normal", "Pause", "Skip", "NoneAuto"], "description": "节点执行策略:Normal-正常执行, Pause-暂停执行, Skip-跳过执行, NoneAuto-非自动执行" }, "id": { "type": "string", "description": "节点唯一标识符" }, "timeout": { "type": "integer", "minimum": 0, "description": "执行超时时间(单位:秒)" }, "instanceMode": { "type": "string", "enum": ["T+1", "Immediately"], "description": "实例生成模式:T+1-次日生成, Immediately-立即生成" }, "rerunMode": { "type": "string", "enum": ["Allowed", "Denied", "FailureAllowed"], "description": "重跑策略:Allowed-允许重跑, Denied-禁止重跑, FailureAllowed-失败时允许重跑" }, "rerunTimes": { "type": "integer", "minimum": 0, "description": "最大重跑次数" }, "rerunInterval": { "type": "integer", "minimum": 0, "description": "重跑间隔时间(单位:秒)" }, "datasource": { "type": "object", "description": "数据源配置", "required": ["name", "type"], "properties": { "name": { "type": "string", "description": "数据源名称" }, "type": { "type": "string", "enum": ["odps"], "description": "数据源类型(当前仅支持odps)" } } }, "script": { "type": "object", "description": "节点执行脚本配置", "required": ["path", "runtime"], "properties": { "language": { "type": "string", "description": "脚本语言类型" }, "path": { "type": "string", "description": "脚本存储绝对路径,结尾必须是节点名称 如:root/file_name" }, "runtime": { "type": "object", "description": "运行时环境配置", "required": ["command"], "properties": { "command": { "type": "string", "enum": ["ODPS_SQL"], "description": "执行命令" }, "cu": { "type": "string", "description": "计算资源单位配置" } } } } }, "trigger": { "type": "object", "description": "节点触发策略配置", "required": ["type"], "properties": { "type": { "type": "string", "enum": ["Scheduler", "Manual", "Streaming", "None"], "description": "触发类型:Scheduler-定时调度, Manual-手动触发, Streaming-流式触发, None-无触发" }, "cron": { "type": "string", "description": "Cron表达式(仅适用于Scheduler类型)" }, "startTime": { "type": "string", "format": "yyyy-MM-dd hh:mm:ss", "description": "调度开始时间" }, "endTime": { "type": "string", "format": "yyyy-MM-dd hh:mm:ss", "description": "调度结束时间" } } }, "runtimeResource": { "type": "object", "description": "运行时资源配置", "required": ["resourceGroup"], "properties": { "resourceGroup": { "type": "string", "description": "资源组唯一标识(identifier)" } } }, "name": { "type": "string", "description": "节点名称" }, "owner": { "type": "string", "description": "节点负责人" }, "inputs": { "type": "object", "description": "节点输入配置", "properties": { "nodeOutputs": { "type": "array", "description": "输入依赖列表", "items": { "type": "object", "required": ["data"], "properties": { "data": { "type": "string", "description": "输入依赖标识" }, "refTableName": { "type": "string", "description": "关联数据表名称(当artifactType为Table时必填)" }, "isDefault": { "type": "boolean", "description": "是否默认输入项" } } } } } }, "outputs": { "type": "object", "description": "节点输入配置", "properties": { "nodeOutputs": { "type": "array", "description": "输入依赖列表", "items": { "type": "object", "required": ["data"], "properties": { "data": { "type": "string", "description": "输入依赖标识" }, "refTableName": { "type": "string", "description": "关联数据表名称(当artifactType为Table时必填)" }, "isDefault": { "type": "boolean", "description": "是否默认输入项" } } } } } } } } } } } } }
ContainerIdNo当你需要将节点创建在一个容器内部时,你需要指定这个参数。该参数为一个容器的唯一标识,这个容器可以是一个Workflow或者一个容器节点。><notice>该参数填写后,FlowSpec中定义的path字段将无效></notice>
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It states '创建' (create) which implies a write/mutation operation, but provides no information about permissions required, whether the creation is reversible, what happens on failure, rate limits, or what the response contains. For a complex creation tool with 4 parameters and nested specifications, this is completely inadequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

While technically concise (two sentences), the description is under-specified rather than efficiently informative. The first sentence is a tautology that adds no value, and the second sentence is procedural metadata about MCP Resources rather than explanatory content. Neither sentence helps an AI agent understand what the tool actually does or how to use it effectively.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex creation tool with 4 parameters (including a deeply nested Spec object), no annotations, and no output schema, the description is completely inadequate. It provides no information about what gets created, the creation context, behavioral characteristics, or expected outcomes. The agent would need to rely entirely on the input schema, which documents parameters but not the tool's purpose or behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 all parameters thoroughly. The description adds no parameter information whatsoever - it doesn't mention ProjectId, Scene, Spec, or ContainerId. However, since the schema provides complete descriptions, the baseline score of 3 is appropriate as the description doesn't need to compensate for schema gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description '创建数据开发节点' (Create data development node) is a tautology that essentially restates the tool name 'CreateNode' in Chinese. It provides no specific verb or resource details beyond the name, and doesn't distinguish this tool from its many siblings (like CreateWorkflowDefinition, CreateTask, etc.). The English note about MCP Resource is procedural rather than explanatory.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides absolutely no guidance on when to use this tool versus alternatives. There are many sibling tools for creating various resources (workflows, tasks, APIs, etc.), but the description offers no context about when this specific node creation tool is appropriate. The MCP Resource note is about how to use the tool, not when to choose it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aliyun/alibabacloud-dataworks-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server