Skip to main content
Glama

Draw on a Whiteboard

edit_board

Add, move, restyle or remove shapes on a Whiteboard. Shapes are keyed by an id you choose; sending the same id again changes that shape, and null removes it. People with the board open see the change within a second, and it is recorded as yours. Shapes people drew themselves are read with read_board but not changed here.

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": {
      "artifact_id": "<artifact_id>",
      "shapes": "<shapes>"
    },
    "name": "edit_board"
  }
}

Input Schema

NameRequiredDescriptionDefault
shapesYesShapes by id (1–64 letters, digits, - or _), each { type, x, y, w, h, z?, color?, text?, frame?, points? }, or null to remove one you drew. type is rect, ellipse, sticky, text, arrow (a line from x,y to x+w,y+h), pen (points is a flat [x0, y0, x1, y1, …] list relative to x,y) or frame (a named area; text is its name). color is ink, gray, red, orange, yellow, green, blue or violet. text is the shape's label. frame puts the shape in the frame with that id. z orders them: higher draws on top. Coordinates are board pixels, y grows downward; a sticky is about 200×200. At most 500 a call.
artifact_idYesThe Artifact id (art_…): the last part of its link, as in bisque.cloud/documents/art_…, /pages/art_… or /artifacts/art_….

Output Schema

NameRequiredDescriptionDefault
urlNo
changedYes
artifact_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations it discloses upsert-by-id semantics, deletion via null, sub-second propagation to viewers with the change attributed to the caller, and a hard scope limit that other people's shapes are immutable here. That authorship and propagation detail is exactly the context annotations cannot express.

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?

Three tight sentences, front-loaded with the verb+resource, then the id/update mechanism, then realtime and scope behavior. No sentence is filler and nothing is buried at the end that belongs at the start.

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?

For a mutation tool with rich schema and an output schema available, the description covers what an agent needs: what can be changed, how identity works, deletion, visibility to collaborators, and the boundary against other people's content. No material gap remains.

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?

Schema coverage is 100% and the schema already documents shape fields, coordinate space, enums and the 500-per-call cap. The description still adds meaning the schema does not: that the id namespace is caller-chosen and that reusing an id is an update rather than a duplicate.

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 first sentence names a specific verb set (add, move, restyle, remove) and the exact resource (shapes on a Whiteboard). The closing sentence explicitly contrasts with the read_board sibling, so an agent can separate mutation from reading 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 states the operating context clearly: shapes are keyed by a caller-chosen id, resending an id mutates it, null deletes it, and other people's shapes must be read with read_board rather than changed here. It stops short of explicit when-not-to-use guidance (e.g., creating a board, deleting a whole artifact), but the read/edit boundary is unambiguous.

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.

Resources