Skip to main content
Glama
nonead

nUR MCP Server

by nonead

draw_rectangle

Draws rectangles or squares on specified planes by defining origin coordinates, width, and height for Universal Robots control through the nUR MCP Server.

Instructions

给定起点位置和边长,在水平或竖直方向画一个正方形 origin:画长方形时TCP的起点位置 width:长(米) height:宽(米) coordinate:圆所在的平面。z:圆形所在的平面与基座所在平面垂直,其它:圆形所在的平面与基座所在平面平行。默认值:z。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ipYes
originYes
widthYes
heightYes
coordinateNoz

Implementation Reference

  • The implementation of the 'draw_rectangle' tool handler. Decorated with @mcp.tool(), which registers it with the FastMCP server. The function constructs waypoints for a rectangle based on origin, width, height, and coordinate plane, generates a URScript program using movel commands to trace the rectangle, sends it to the robot via RealTimeClient.SendProgram, and handles connection checks and errors.
    @mcp.tool()
    def draw_rectangle(ip: str, origin: list, width: float, height: float, coordinate="z"):
        """给定起点位置和边长,在水平或竖直方向画一个正方形
                origin:画长方形时TCP的起点位置
                width:长(米)
                height:宽(米)
                coordinate:圆所在的平面。z:圆形所在的平面与基座所在平面垂直,其它:圆形所在的平面与基座所在平面平行。默认值:z。"""
    
        try:
            if '连接失败' in link_check(ip):
                return return_msg(f"与机器人的连接已断开。")
            wp_1 = [origin[0], origin[1], origin[2], origin[3], origin[4], origin[5]]
            wp_2 = [origin[0], origin[1], origin[2], origin[3], origin[4], origin[5]]
            wp_3 = [origin[0], origin[1], origin[2], origin[3], origin[4], origin[5]]
            if coordinate.lower() == "z":
                wp_1[1] = wp_1[1] + width
    
                wp_2[1] = wp_2[1] + width
                wp_2[2] = wp_2[2] - height
    
                wp_3[2] = wp_3[2] - height
    
            else:
                wp_1[1] = wp_1[1] + width
    
                wp_2[1] = wp_2[1] + width
                wp_2[0] = wp_2[0] + height
    
                wp_3[0] = wp_3[0] + height
    
            cmd = (f"def my_program():\n"
                   f"  movel(p{str(origin)}, a=1, v=0.25)\n"
                   f"  movel(p{str(wp_1)}, a=1, v=0.25)\n"
                   f"  movel(p{str(wp_2)}, a=1, v=0.25)\n"
                   f"  movel(p{str(wp_3)}, a=1, v=0.25)\n"
                   f"  movel(p{str(origin)}, a=1, v=0.25)\nend\nmy_program()")
            logger.info(f"draw_rectangle 发送脚本:\n{cmd}")
            robot_list[ip].robotConnector.RealTimeClient.SendProgram(cmd)
            return return_msg(f"命令已发送:{cmd}")
        except Exception as e:
            logger.error(f"命令发送失败: {str(e)}")
            return return_msg(f"命令发送失败: {str(e)}")
Behavior2/5

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

With no annotations provided, the description carries full burden but provides minimal behavioral context. It mentions the tool draws shapes but doesn't describe what actually happens (e.g., robotic arm movement, whether it's a simulation or physical operation, execution time, error conditions, or safety considerations).

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

Conciseness3/5

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

Reasonably concise with four parameter explanations, but the structure is poor with inconsistent formatting and a confusing coordinate explanation that mixes rectangle/circle concepts. The first sentence states the purpose clearly, but subsequent parameter details are disorganized.

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

Completeness2/5

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

Incomplete for a 5-parameter robotic control tool with no annotations and no output schema. The description doesn't explain what the tool returns, error conditions, execution behavior, or how it interacts with the robot system. The confusing coordinate explanation and missing 'ip' parameter documentation create significant gaps.

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

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate but provides incomplete parameter semantics. It explains origin, width, height, and coordinate but misses the 'ip' parameter entirely. The coordinate explanation is confusing (mixing rectangle and circle concepts) and doesn't clarify valid values beyond 'z' default.

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

Purpose3/5

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

The description states the tool draws a rectangle/square given position and dimensions, which clarifies the basic purpose. However, it's vague about the context (robotic arm drawing) and doesn't distinguish from siblings like draw_square or draw_circle beyond mentioning 'horizontal or vertical direction'.

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

Usage Guidelines2/5

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

No explicit guidance on when to use this tool versus alternatives like draw_square or draw_circle. The description mentions 'horizontal or vertical direction' which might imply orientation constraints, but doesn't clarify when to choose this over other drawing tools or movement commands.

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/nonead/nUR-MCP-SERVER'

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