Rapier - Markdown Editor & Art

Open Rapier

open

Use this when the person wants a document, notes, a list, a table, a diagram they can drag to rearrange or a drawing that they can keep editing by hand, or asks to open or continue one. Use this too when they want to paint in watercolor or learn it: the paint is simulated, so pigment flows, mixes, blooms and dries on textured paper, and they can paint by hand beside your strokes on one sheet. Free, no account, in the chat or any browser. Not for an answer they will only read. Create {text, filename}, resume {document}, open a Note {document, note}, create one {document, note:"new", text, title} (title only there), or import a host file {file}. Put a new document's whole first text in open, drawings and paintings included: one call, no edit (a painting then waits for the person's editor). Returns revision and whole text when it fits a page; otherwise a document map. A browser code goes to show {target:"pair", code}. Share editor_url when available; keep document private.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "open"
  }
}

Input Schema

Name	Required	Description
`url`	No	This Door's editor_url, through its authorized connection. Use alone; other URLs are not fetched.
`file`	No
`note`	No
`text`	No
`agent`	No	Your display name on acts; never grants authority.
`title`	No
`document`	No
`filename`	No
`createToken`	No
`operation_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already mark this as a non-read-only, non-destructive, open-world, non-idempotent mutation, and the description adds real context beyond them: the return shape ('Returns revision and whole text when it fits a page; otherwise a document map'), the side effect that a painting 'waits for the person's editor', the no-account/free access model, and a privacy instruction. It leaves the semantics of createToken, operation_id and agent unexplained, which is a gap for an open-world mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with the trigger condition, but the body is a dense run-on that mixes marketing asides ('Free, no account, in the chat or any browser') and two paragraphs' worth of mode routing into one block of prose. Every clause is roughly load-bearing, yet the lack of structure makes the mode-selection rules easy to misread.

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 10-parameter, open-world tool with no output schema, the description covers the return values, the create-vs-resume modes, and the privacy expectation, which is substantial. The missing pieces are the meaning of agent, createToken and operation_id and how they interact with the create modes.

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 20%, so the description must compensate, and it does for most of the surface: text, filename, document (resume), note (open or note:"new" with title only in that mode), file (host import), and url ('Use alone; other URLs are not fetched'). Three parameters — agent, createToken, operation_id — get no treatment anywhere, which keeps it short of a 5.

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 states a specific resource set (document, notes, list, table, diagram, drawing, painting) and the verb (open/continue/create), and it distinguishes itself from siblings by name and behavior: 'Not for an answer they will only read' points away from read, and 'one call, no edit' points away from edit. An agent can select it without opening the 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 trigger phrasing ('when the person wants ... or asks to open or continue one'), an explicit when-not ('Not for an answer they will only read'), and a routing rule for a competing case ('A browser code goes to show {target:"pair", code}'). It also says to share editor_url when available, which is an operational guideline rather than a parameter restatement.

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

All Rapier - Markdown Editor & Art 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.