Compose Preview Catalogs

Preview Catalogs

catalog_library

Open the hosted preview catalog browser app. With no arguments it lists every catalog with its preview count only; pass projectId to list one catalog's previews. To find previews without the app, call catalog_list_projects, then catalog_list_previews with a catalog id. Also opens from the ChatGPT/Codex sidebar.

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": "catalog_library"
  }
}

Input Schema

Name	Required	Description	Default
`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.
`projectId`	No	A catalog id from catalog_list_projects whose previews to list.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedSep 30, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the full burden, and it discloses key behavioral traits: this opens an interactive hosted app rather than returning data, output differs by argument, and it can also be launched from the ChatGPT/Codex sidebar. It does not cover auth/permission requirements or failure behavior, though the token parameter description partially addresses session-token handling.

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?

Three tight sentences, front-loaded with the core purpose and the two modes; every sentence adds routing or parameter value. The trailing sidebar note is a mild fragment but still relevant context.

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 2-param app-launcher with a fully-described schema and an output schema present, the description covers purpose, both argument modes, sibling alternatives, and launch surfaces. Return-value explanation is rightly omitted given the output schema; only failure/permission behavior is unaddressed.

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 baseline is 3, but the description adds meaning the schema does not: omitting projectId changes the tool into a full-catalog listing with preview counts only, and projectId is sourced from catalog_list_projects. This clarifies the conditional semantics of the optional parameter.

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?

States a specific verb (Open) and resource (hosted preview catalog browser app), then immediately clarifies its two modes: no-arg catalog listing vs. projectId-scoped preview listing. An agent can distinguish it from catalog_list_projects, catalog_list_previews, and ui_builder_open without opening any 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?

Explicitly states when to use each mode ('With no arguments it lists every catalog...; pass projectId to list one catalog's previews') and names the non-app alternative path (catalog_list_projects then catalog_list_previews with a catalog id). Routing guidance is complete.

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

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.