Skip to main content
Glama
KTCrisis

arch7

by KTCrisis
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

create_diagram

Create Excalidraw diagrams from node and connection data. Define nodes with optional styling; the tool automatically layouts and renders the diagram.

Instructions

Create a new Excalidraw diagram from structured node and connection data.

The LLM provides a relationship map - this tool handles layout, styling, and rendering. No need to specify coordinates.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nodesYesList of nodes. Each dict has: - id (str, required): Unique identifier - label (str, required): Display text - component_type (str, optional): Technology name for auto-styling (e.g., "kafka", "postgresql", "redis", "nginx", "kubernetes"). If omitted, the label is used for auto-detection. - shape (str, optional): Override shape - "rectangle", "diamond", "ellipse", "circle", "stadium", "parallelogram" - color (str, optional): Hex color (e.g. "#6366f1") to override the auto-detected background fill. Stroke is darkened automatically. - planned (bool, optional): If true, render as a planned/future element (dashed stroke + 60% opacity). Default: false.
connectionsYesList of connections. Each dict has: - from_id (str, required): Source node id - to_id (str, required): Target node id - label (str, optional): Edge label text - style (str, optional): "solid", "dashed", "dotted", "thick"
output_pathYesFile path to save the .excalidraw file (e.g., "./arch.excalidraw")
directionNoLayout direction - "LR" (left-right), "TD" (top-down), "BT" (bottom-up), "RL" (right-left). Default: "LR"LR
themeNoColor theme - "default", "dark", "colorful", "professional". Default: "default". "professional" uses clean lines (no hand-drawn effect) and Helvetica font.default
subgraphsNoOptional list of groups (supports nesting). Each dict has: - id (str, required): Group identifier - label (str, required): Display label for the container - node_ids (list[str], required): Direct node ids inside this group - child_ids (list[str], optional): IDs of nested child subgroups. Parent containers automatically wrap around their children. - component_type (str, optional): Technology for container icon (e.g., "gke" or "googlecloud" shows a GCP logo top-right). Useful for multi-cloud diagrams.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Tool Definition Quality

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries full burden. It discloses automated layout/styling (e.g., 'no need to specify coordinates'), but does not mention return value, error handling, or limitations. The output schema exists but isn't referenced.

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?

Two short, front-loaded sentences with zero wasted words. Every sentence adds value: first states the action, second clarifies automation and reduces cognitive load for the LLM.

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 6 parameters and existence of output schema, the description covers the core task adequately. Missing explicit info on return value (but output schema exists, so not required per rubric). Minor gap: no mention of file saving behavior even though output_path parameter implies it.

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 baseline is 3. The main description adds minimal extra meaning beyond schema: it reiterates that coordinates are not needed, but parameter details are in schema. No significant enhancement.

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?

Description clearly states 'Create a new Excalidraw diagram from structured node and connection data', using a specific verb and resource. It distinguishes from sibling tools (get_diagram_info, mermaid_to_excalidraw, modify_diagram) by focusing on creation, handling layout/styling/rendering automatically.

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

Usage Guidelines3/5

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

The description implies the tool is for creating diagrams from structured data but provides no explicit guidance on when to use it versus siblings (e.g., not for modifying existing diagrams or converting from Mermaid). No 'when not to use' or alternative recommendations.

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/KTCrisis/arch7'

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