Skip to main content
Glama

AtomicViz Diagrams

Create an interactive diagram

create_diagram
Read-only

Creates an interactive diagram in the conversation from nodes and edges you supply. Use it when the user asks to draw, diagram, map or visualize how the parts of something relate: system architecture, services and the calls between them, data models, dependency trees, workflows, organizations, knowledge maps. Not for charts of numeric data. In the diagram the user can collapse and expand boxes, regroup at each level of nesting, focus on an item and what connects to it, show clusters and cycles, and search, hide and export. The server checks the diagram and stores nothing. STRUCTURE: every node has a unique 'id'. A node with no 'parent' is drawn as a box of its own; a node WITH a 'parent' is drawn as a ROW inside its parent's box (an endpoint inside a service, a column inside a table) and the parent can be collapsed. 'group' (top-level nodes only) draws a labelled boundary around nodes, nested with '/': 'AWS/VPC' puts the node in a VPC box inside an AWS box. If you use groups, give EVERY top-level node a group: the views that draw groups as closed or stacked boxes are offered only when no node is left out. Edges run between any two nodes, rows included; give an edge a short 'label' only when the relation is not obvious ('HTTPS', 'publishes'). Optional per node: 'description' (shown on hover; add one only where the label is not enough), 'link' (an https URL, opened on double-click), 'color', 'kind': 'field' for an attribute-style row, 'collapsed': true to start folded. Optional per edge: 'color', 'style' ('dashed' for async or optional, 'dotted' for weak). Keep it legible: prefer grouping and nesting over hundreds of top-level boxes; use color for a category, not decoration.

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": {
      "nodes": "<nodes>"
    },
    "name": "create_diagram"
  }
}

Input Schema

NameRequiredDescriptionDefault
edgesNo
nodesYes
titleNoDiagram title, shown as its name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'The server checks the diagram and stores nothing,' which tells the agent validation happens but no persistence. It goes further by disclosing the interactive surface the user gets (collapse/expand, regroup, focus, clusters and cycles, search, hide, export) and a non-obvious behavioral rule: group-based views are only offered when every top-level node has a group.

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

Conciseness4/5

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

Front-loaded with purpose, then usage, then behavior, then a clearly labelled STRUCTURE block, so an agent can stop reading early. It is long, and a few clauses restate schema text verbatim ('link' as an https URL opened on double-click, 'collapsed': true to start folded), which is redundant against structured data.

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

Completeness5/5

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

No output schema exists, and the description covers what the agent needs: the diagram renders in the conversation, what the user can do with it, that nothing is stored, and the structural rules for nodes, parents, groups and edges. Nothing required to call it correctly is missing.

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

Parameters5/5

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

Schema coverage is only 33%, but the description compensates heavily: 'parent' means the node is drawn as a row inside its parent's box and the parent becomes collapsible; 'group' draws a labelled boundary nested with '/' ('AWS/VPC'); 'kind: field' marks attribute-style rows; 'collapsed' starts folded; edge 'style' dashed means async or optional and dotted means weak. These are semantic consequences the schema does not convey.

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?

States a specific verb and resource ('Creates an interactive diagram in the conversation from nodes and edges you supply') and immediately bounds the domain with 'Not for charts of numeric data.' An agent can tell exactly what this produces and what it does not.

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

Usage Guidelines5/5

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

Gives an explicit trigger ('when the user asks to draw, diagram, map or visualize how the parts of something relate') with a concrete enumeration of fitting subjects (architecture, data models, dependency trees, workflows), plus an explicit exclusion for numeric charts. No sibling tools exist, so no alternative routing is needed.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.