Skip to main content
Glama

draw

Draw on a board: boxes (rectangle, ellipse, diamond), text, arrows between two shapes, and frames that hold shapes under a name. Everyone with the board open sees it at once. Give shapes your own short ids to join them with arrows and put them in frames in the same call. Leave out x and y, and the board lays new shapes out along their arrows, below what is already there. A box sizes itself to its text unless you give a width and height, and a frame wraps the shapes in it.

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": {
      "board": "<board>",
      "shapes": "<shapes>"
    },
    "name": "draw"
  }
}

Input Schema

NameRequiredDescriptionDefault
boardYesThe board's id, as in its URL.
shapesYes
directionNoWhich way arrows run between the shapes the board places: right unless given.

Output Schema

NameRequiredDescriptionDefault
idsYesEach shape's id, in the order given.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the single destructiveHint=false annotation, the description discloses meaningful behavior: everyone with the board open sees changes at once, shapes auto-layout when x/y are omitted, boxes auto-size to text unless width/height are given, and frames wrap contained shapes. It does not cover permissions, limits, or error behavior, but it adds substantial operational context.

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 description is front-loaded with the core operation and then layers on important defaults and call-shaping advice. It is dense but each sentence adds useful information, with only minor overlap against schema descriptions.

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 rich nested shape schema and the presence of an output schema, the description covers the main behavioral gaps: visibility to collaborators, id-based joining, automatic layout, sizing defaults, and frame wrapping. It is complete enough to call correctly, though it still leaves sibling-tool routing unaddressed.

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

Parameters4/5

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

The schema already documents many shape fields, but the description adds relational meaning: ids can join arrows and frames in one call, omitted coordinates trigger automatic layout along arrows below existing content, and frames automatically wrap their children. This goes beyond the 67% schema description coverage and helps an agent reason about how the parameters interact.

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

Purpose4/5

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

The description states a specific verb and resource: drawing boxes, text, arrows, and frames on a board. It is clear what the tool does, but it does not explicitly distinguish itself from sibling tools such as erase or read_board.

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?

It gives useful invocation guidance, such as supplying ids to join arrows and frames in the same call and omitting x/y to let the board auto-place shapes. However, it does not say when to use this tool versus alternatives like read_board, erase, or sync, so usage is only implied by the operation.

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.