Skip to main content
Glama

block_diagram

Draw architecture diagrams as labeled boxes joined by arrows or lines, with configurable direction, style, and title for pipelines, stacks, and flow charts.

Instructions

Draw an architecture diagram: a sequence of labeled boxes joined by connectors — the structured counterpart to shape_text. Give it blocks (each a label; use \n for a multi-line label) and it lays them out as boxes with arrows between, sized to the longest label. Perfect for a transformer stack, a pipeline, or a flow chart. Choose direction (down/up/right/left), style (unicode rounded, ascii, or double lines), and an optional title.

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": {
      "blocks": "<blocks>"
    },
    "name": "block_diagram"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
gapNoConnector length in cells between boxes.
alignNocenter
pad_xNoHorizontal padding inside each box.
styleNoBox charset: unicode (rounded), ascii (portable +-|), or double lines.unicode
titleNoOptional heading centered above the diagram.
blocksYesThe labels, in flow order. Each becomes a box; use \n for multiple lines.
connectorNoWhat joins the boxes: an arrowhead, a plain line, or nothing.arrow
directionNoFlow direction. down/up stack vertically; right/left run horizontally.down

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

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 the full disclosure burden. It usefully explains the rendered output (boxes sized to the longest label, arrows between, optional title) but says nothing about canvas interaction — whether x/y position it on an existing canvas, whether it overwrites content, or the 40-block cap.

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?

The purpose and the core interaction (`blocks` in, laid-out boxes out) are front-loaded in the first sentence, with configuration options consolidated afterward. The closing "Perfect for..." sentence is somewhat promotional but earns its place by grounding the tool in concrete use cases.

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

Completeness3/5

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

For a 10-parameter drawing tool with no annotations and no output schema, the description covers the conceptual model and the most agent-relevant knobs but leaves positioning parameters and canvas side effects unexplained. An agent can call it correctly for the common case, yet may be surprised by where the diagram lands.

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 70%, so the schema already documents most parameters. The description adds only light meaning for `blocks` (multi-line via \n) and repeats `direction`, `style`, and `title` enum surface without expanding on them, and is silent on `x`, `y`, `gap`, `align`, `pad_x`, and `connector`.

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 opens with a specific verb and resource ("Draw an architecture diagram") and immediately scopes it as "a sequence of labeled boxes joined by connectors," then explicitly positions it as "the structured counterpart to shape_text," letting an agent distinguish it from that sibling without opening either schema.

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?

It gives concrete use cases ("a transformer stack, a pipeline, or a flow chart") and signals the relationship to shape_text as the free-form alternative. It stops short of explicit when-not guidance versus other diagram siblings like tree_diagram or draw_block, which is the only reason it isn't a 5.

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