staruml-mcp

Overview Schema Source Related Servers Discussions Admin

create_edge_with_view

Connect views on a diagram with a typed relationship edge (UMLAssociation, UMLControlFlow, etc.) using source and target view IDs.

Instructions

Connect two existing Views on a diagram with a typed relationship edge. Edge types: 'UMLAssociation' (use case), 'UMLControlFlow' (activity), 'UMLMessage' (sequence), 'UMLGeneralization', 'UMLDependency'. tailViewId is the source, headViewId is the target. Use view IDs from create_element_with_view results. Requires staruml-mcp-extension to be installed in StarUML. Install from https://github.com/ezrabrilliant/staruml-mcp-extension

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "<type>",
      "parentId": "<parentId>",
      "diagramId": "<diagramId>",
      "tailViewId": "<tailViewId>",
      "headViewId": "<headViewId>"
    },
    "name": "create_edge_with_view"
  }
}

Input Schema

Name	Required	Description
`x`	No	Edge tail X coordinate (required for SeqMessage vertical positioning)
`y`	No	Edge tail Y coordinate (REQUIRED for UMLMessage in sequence diagrams — determines vertical position of the message; without this, all messages stack at same y)
`x2`	No	Edge head X coordinate
`y2`	No	Edge head Y coordinate (defaults to y if omitted)
`name`	No	Optional edge label
`type`	Yes	Edge metamodel type: 'UMLAssociation', 'UMLControlFlow', 'UMLMessage', 'UMLGeneralization', 'UMLDependency'
`parentId`	Yes	Owning model's _id
`diagramId`	Yes	Diagram's _id
`headViewId`	Yes	Target view _id (from create_element_with_view)
`tailViewId`	Yes	Source view _id (from create_element_with_view)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.3Jul 28, 2026

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description must cover behavioral traits. It explains the edge types, source/target orientation, and positional requirements. However, it doesn't mention whether the operation is reversible, error conditions, or what the tool returns on success.

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

Conciseness5/5

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

The description is brief and to the point, using separate sentences for purpose, edge types, tail/head clarification, prerequisites, and installation URL. No redundant or unnecessary text.

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

Completeness4/5

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

Given the high parameter count and no output schema, the description adequately covers the tool's function, required inputs, and prerequisites. It lacks details on return values or error handling, but the context signals indicate no output schema exists, so the description is reasonably complete.

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?

All 10 parameters have schema descriptions (100% coverage), so the baseline is 3. The description adds minimal new meaning beyond the schema, such as clarifying tail/head orientation, but largely restates schema info.

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

Purpose5/5

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

The description clearly states the tool connects two views with a typed relationship edge, specifies available edge types, and distinguishes from sibling tools like create_element_with_view which creates elements, not edges.

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

Usage Guidelines4/5

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

The description explains that view IDs come from create_element_with_view and that the extension must be installed. It doesn't explicitly contrast with other tools, but the purpose is specific and no alternative edge tools exist among siblings.

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