wren

Plan a handwritten Wren notebook

plan_notebook

Destructive

Plan a 1-30 page handwritten Wren notebook and write its cover and contents (page 1; over 8 pages: a cover page and contents pages). The cover is not a slot: slots are the content pages, numbered from 1. Then write each slot with write_notebook_page (target.noteId + planSlot), one call per slot. Pass noteId to extend a plan: new pages become the next slots after the existing ones. Same topic as an earlier note → pass its noteId. Optional: part (a topic group such as "Obstetrics", never a page title) per page; coverFigure (one on-topic sketch) makes a better cover.

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": {
      "title": "<title>",
      "pages": "<pages>",
      "llm_model": "<llm_model>"
    },
    "name": "plan_notebook"
  }
}

Input Schema

Name	Required	Description
`pages`	Yes
`title`	Yes
`accent`	No
`noteId`	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.
`coverFigure`	No	e.g. formula {latex}, graph_2d {curves:[{expr}]}, flowchart; drawn in one pen.
`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	Default
`ok`	Yes
`mode`	No
`plan`	No
`title`	No
`noteId`	No
`pageId`	No
`noteUrl`	No
`outline`	No
`location`	No
`pageCount`	No
`pageNumber`	No
`strokeCount`	No
`semanticType`	No
`strokeGroupId`	No
`conversationNote`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 14, 2026
- addedInput schema / properties / context / additionalProperties
```
Added value: +false
```
- addedInput schema / properties / coverFigure / additionalProperties
```
Added value: +false
```
- addedInput schema / properties / pages / items / additionalProperties
```
Added value: +false
```
First observedNov 14, 2026

TDQS

A4.3/5.0

Behavior3/5

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

The description adds real behavioral context the annotations don't carry — the plan-then-write workflow, slot numbering starting at 1, and that reuse of noteId appends rather than replaces. However, annotations declare destructiveHint=true and the description never says what an existing plan loses or whether re-planning overwrites pages, which is the most important risk to disclose for a destructive, non-idempotent, open-world call.

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 primary action and tightly packed with no filler. It is dense to the point of being clause-heavy (slot numbering, extension semantics, and optional params in one block), but every sentence carries operational information.

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 9-parameter tool with nested objects that exists as the first half of a two-call workflow, the description covers the handoff to write_notebook_page and the extension path, and an output schema exists so return values need no explanation. The gaps are the undisclosed overwrite behavior and the unmentioned context/subject/accent grouping, which matter for a destructive mutation.

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 only 33%, but the description compensates on the tricky fields: it clarifies that pages are slots numbered from 1 with the cover excluded, that each page may carry a part ('a topic group such as "Obstetrics", never a page title'), and that coverFigure is a single on-topic sketch that improves the cover. It says nothing about accent, subject, or the context object, so some meaning is still left to the schema.

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 names a specific verb and artifact ('Plan a 1-30 page handwritten Wren notebook') and immediately states what the call does and does not produce: cover and contents are written here, but 'the cover is not a slot' and content pages are written separately with write_notebook_page. An agent can distinguish this planner from the page-writer 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 gives explicit routing: one write_notebook_page call per slot using target.noteId + planSlot, pass noteId to extend a plan so new pages append after existing slots, and pass the noteId of an earlier note on the same topic. It also marks part and coverFigure as optional with concrete conditions for using them, leaving little to inference.

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?