Compose Preview Catalogs

ui_builder_create_design

Create a design, either from a whole document you supply or by copying an existing design named by fromDesignId. Copying is usually right: a document's catalogPin must match a catalog revision this server serves, and a copy carries one that does. A document whose home is an existing design on this server is refused with a compose-preview-decision/v1 choice to put to the person — or, when your client supports form elicitation on this connection, the person is asked in a form and the call acts on their answer.

Input Schema

TableJSON Schema

Name	Required	Description
`title`	No
`token`	No	A grant token from poll_access, when you cannot set the X-Compose-Preview-Token header yourself — an MCP client fixes its headers at connect time, so this is how a token approved during this session is used in it. Prefer the header where you control it.
`designId`	Yes	The id for the new design.
`document`	No	A whole DesignDocumentV1.
`agentName`	No	Optional agent/client name shown to design viewers; self-reported.
`agentModel`	No	Optional current model name shown to design viewers; self-reported. Omit when unknown.
`visibility`	No	Defaults to the server's configured visibility, which is private unless the operator chose public. Public allows anyone with the link to view; editing still requires explicit access.
`fromDesignId`	No	Copy this design's document instead.
`includeCatalog`	No	Embed the pinned catalog in the returned snapshot. Defaults to false.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 4, 2026

addedInput schema / properties / agentModel

Added value: +{
+  "description": "Optional current model name shown to design viewers; self-reported. Omit when unknown.",
+  "maxLength": 80,
+  "type": "string"
+}

addedInput schema / properties / agentName

Added value: +{
+  "description": "Optional agent/client name shown to design viewers; self-reported.",
+  "maxLength": 80,
+  "type": "string"
+}

Changed2 schema fields changedOct 4, 2026

removedInput schema / properties / visibility / default
```
Removed value: -"private"
```

changedInput schema / properties / visibility / description

Previous value: -"Private by default. Public allows anyone with the link to view; editing still requires explicit access."New value: +"Defaults to the server's configured visibility, which is private unless the operator chose public. Public allows anyone with the link to view; editing still requires explicit access."

Changed1 schema field changedOct 3, 2026

addedInput schema / properties / visibility

Added value: +{
+  "default": "private",
+  "description": "Private by default. Public allows anyone with the link to view; editing still requires explicit access.",
+  "enum": [
+    "private",
+    "public"
+  ],
+  "type": "string"
+}

Changed1 schema field changedSep 30, 2026
- changedOutput schema / (root)
```
Previous value: -nullNew value: +{
+  "type": "object"
+}
```
First observedSep 30, 2026

TDQS

A4.2/5.0

Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so well. It discloses refusal behavior, the `compose-preview-decision/v1` response, form-elicitation fallback, catalog-pin compatibility requirements, and token/header handling context. These are meaningful operational traits beyond the schema.

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 appropriately sized and front-loads the core create action and its two modes. The later sentence about refusal and form elicitation is dense and slightly run-on, but every clause adds relevant procedural 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 complex 9-parameter creation tool with an output schema, the description covers the important behavioral context: creation modes, copying preference, catalog constraint, and refusal path. It omits permission/visibility details and some operational edges, but the output schema and parameter schema carry much of that burden.

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 high (89%), so the schema already documents most parameters. The description still adds meaningful semantics for `document` and `fromDesignId`, especially around `catalogPin` compatibility and `home`-based refusal, which helps the agent choose between supplying a document and copying one.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

It gives a specific verb and resource: create a design. It also clearly separates two creation modes (supply a whole `document` vs copy via `fromDesignId`). However, it does not explicitly differentiate this tool from close siblings such as `ui_builder_fork_design` or `ui_builder_branch_design`, so the sibling distinction is only implicit.

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?

The description gives strong contextual guidance: copying is usually right, supplied documents must have a compatible `catalogPin`, and a document whose `home` is an existing server design will be refused with a `compose-preview-decision/v1` choice. It does not name alternative sibling tools for copying/forking, so the when-to-use guidance is clear but not fully routed.

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

All Compose Preview Catalogs tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.