Skip to main content
Glama

Create a tool document

tools_create_document

Create a new, empty document for the signed-in user in one of the builders. Returns the new id and version. Pass spaceId to start it inside a shared Space the user can edit; without it the document is personal. Pass idempotencyKey and a repeat of the same call returns the document it already made rather than a second one. Give the reader the returned url: it opens the document in its builder.

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": {
      "toolKey": "<toolKey>"
    },
    "name": "tools_create_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoDefaults to the builder's own default.
spaceIdNoA shared Space to start the document in. The user must be its owner or an editor.
toolKeyYesWhich builder: ost | usm | cfd | vsm | noice | wardley | roi | roadmap.
idempotencyKeyNoYour id for this create. Repeating it returns the same document instead of making two.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare this as a non-read-only, non-destructive, closed-world create. The description supplements them with behavior annotations don't carry: the returned id/version/url, the idempotency retry semantics, and the permission precondition that the user must be an owner or editor of the Space. It stops short of describing failure modes or whether an empty document consumes quota.

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?

Four short sentences, front-loaded with the create action and its return values, with no filler. The closing sentence is phrased as an instruction to the caller ('Give the reader the returned url') rather than describing the tool, and the spaceId sentence partially restates the schema's permission note.

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?

With no output schema, the description still covers what comes back (id, version, url), how to construct it (builder via toolKey, optional Space), and retry safety. That is enough for an agent to call it correctly on the first attempt.

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%, so the baseline is 3, but the description adds meaning the schema does not: it explains the consequence of omitting spaceId (personal vs shared) and frames idempotencyKey as a repeat-safety guarantee. Title and toolKey add nothing beyond 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 opens with a specific verb and resource ('Create a new, empty document') and states the scope ('for the signed-in user') plus the builder selection, which cleanly separates it from retrieval siblings like tools_get_document and tools_list_documents. It also states the output up front ('Returns the new id and version').

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 gives concrete conditional guidance: pass spaceId to place the document in a shared Space, omit it for a personal document; pass idempotencyKey to make repeats safe. What is missing is any when-not or explicit alternative routing (e.g., versus apply_commands on an existing document), so it earns 4 rather than 5.

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