wren

Draw one figure in Wren

draw_figure

Destructive

Draw ONE standalone figure in the user's Wren notebook, big on its own page: a graph, labelled diagram, chart, table, timeline, flowchart, mind map, concept map, number line or shapes. Notes, explanations, worked examples, summaries or text to copy go to write_notebook_page (a figure that goes with text: a figure block there). No target: a new note. target.noteId: a new page at the end of that note (same topic -> same note); with target.pageNumber: drawn onto that page if Wren wrote it (mode append keeps its ink, replace redraws it). The result has a private link (noteUrl; opens in the user's Wren account after sign-in): give it to the user.

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": {
      "figure": "<figure>",
      "llm_model": "<llm_model>"
    },
    "name": "draw_figure"
  }
}

Input Schema

Name	Required	Description
`title`	No	A new note's title.
`figure`	Yes
`target`	No
`context`	No
`subject`	No
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.

Output Schema

Name	Required	Description
`ok`	Yes
`title`	No
`noteId`	No
`pageId`	No
`noteUrl`	No	Private link to the note in the user's Wren account (opens after sign-in).
`pageCount`	No
`figureKind`	No
`pageNumber`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 14, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds real context beyond them: pageNumber only draws onto a page if Wren wrote it, mode append preserves existing ink while replace redraws it (explaining the destructive profile), and the result carries a private noteUrl that requires sign-in. These are behavioral facts the annotations cannot convey.

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 two-sentence, colon-driven structure front-loads the core action and the sibling hand-off. It is dense with parenthetical asides and a long figure-kind list, which makes it slightly harder to parse, but no sentence is filler.

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?

For a 7-parameter, nested-object, destructive write tool, the description covers the critical unknowns: destination logic, sibling boundary, overwrite semantics, and the returned link (an output schema also exists). The context and subject parameters get no explanation, which is the main remaining gap.

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 description coverage is only 43%, and the description compensates well for the weakest documented area — target, where it explains noteId (new page at end of that note, same topic to same note) and pageNumber/mode interplay. It leaves context, subject and title unaddressed, relying on the schema's own enum labels and maxLength constraints for those.

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 ONE standalone figure") and enumerates the supported figure kinds (graph, table, timeline, flowchart, mind map, etc.), then explicitly distinguishes itself from write_notebook_page. An agent can tell exactly what this tool produces versus its 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 Guidelines5/5

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

It names the alternative outright: notes, explanations, worked examples, summaries and copy-text go to write_notebook_page, and even clarifies the hybrid case (a figure accompanying text becomes a figure block there). It also spells out the three destination modes — no target, noteId only, noteId plus pageNumber — so the routing decision is fully specified.

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

All wren tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?