Compose Preview Catalogs

ui_builder_await_design

Wait for somebody else to change a design and return what they changed, rather than asking again whether they have. Returns the moment a designer in the browser or another agent commits an edit, as the same update frame the browser's own live socket receives; returns a timedOut reply if nothing happens within waitSeconds, which you answer by calling again with the same cursor. Quote as afterSequence the throughSequence of the delta you last received, or the lastSequence of the last snapshot; a cursor the server no longer retains is answered with a whole snapshot instead of the operations you missed. waitSeconds: 0 checks without blocking. Nothing is lost between calls — the cursor is replayed when you call again — so somebody merely looking at the design does not wake you, and only a committed change does.

Input Schema

TableJSON Schema

Name	Required	Description
`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
`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.
`waitSeconds`	No	Up to 120. Defaults to 25.
`afterSequence`	Yes	The `lastSequence` you last saw, from ui_builder_get_design or a previous wait.
`includeCatalog`	No	When the reply is a whole snapshot, embed the pinned catalog in it. 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"
+}

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

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations, the description carries the full load and does so richly: it discloses the return trigger (a committed edit), the timedOut reply when nothing happens, that a non-retained cursor yields a whole snapshot, that only committed changes wake the caller (not viewers), and that nothing is lost between calls via cursor replay.

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?

Purpose is front-loaded and nearly every clause carries behavioral detail (timeout, cursor retention, non-blocking check). It is a single dense paragraph that runs slightly long, 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 streaming/long-poll tool with an output schema and 7 parameters, the description covers the essentials: cursor lifecycle, timeout handling, snapshot fallback, and wake semantics. Return-value shape is left to the output schema, appropriately. Naming its sibling alternatives would close the 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 coverage is 86%, so the baseline is 3. The description adds real meaning beyond the schema by explaining how to derive afterSequence (the throughSequence of the last delta or lastSequence of the last snapshot) and what waitSeconds: 0 does, going beyond the terse schema hints.

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 precise verb+resource: waiting for somebody else to change a design and returning what they changed. It explicitly contrasts this with 'asking again whether they have,' which distinguishes it from polling-style siblings like ui_builder_check_design without naming them.

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 clear operational context: use it to wait instead of re-asking, answer a timedOut reply by calling again with the same cursor, and use waitSeconds: 0 to check without blocking. The alternative (polling via check_design) is implied rather than named explicitly, so it stops just short of a full when/when-not mapping.

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.