Compose Preview Catalogs

ui_builder_share_design

Share a design with somebody else, or take that sharing back. actorId is the other party's actor id as this server spells it — github:<login> for a signed-in person, operator for the token holder, agent:<fingerprint> for another agent's grant; ui_builder_design_access lists the ones a design already carries. A viewer may read and export, an editor may also change the design, and neither may share it on. Only the design's owner may share it, and an agent acting under an approved grant shares as the person who approved that grant. Pass visibility instead of actorId to choose private or public (read only). Private keeps existing invited collaborators.

Input Schema

TableJSON Schema

Name	Required	Description
`role`	No	editor or viewer. Defaults to viewer.
`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.
`revoke`	No	Take this actor's access away instead.
`actorId`	No	Who to share with, e.g. github:octocat.
`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.
`visibility`	No	Change visibility instead of an actor grant. Public is read only. Private keeps invited collaborators.

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 3, 2026

addedInput schema / properties / visibility

Added value: +{
+  "description": "Change visibility instead of an actor grant. Public is read only. Private keeps invited collaborators.",
+  "enum": [
+    "private",
+    "public"
+  ],
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "designId",
-  "actorId"
-]New value: +[
+  "designId"
+]

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

TDQS

A4.8/5.0

Behavior5/5

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

No annotations are provided, so the description carries the full burden and does so richly: role capabilities (viewer read/export, editor change, neither may reshare), owner-only authorization, agent-shares-as-approver semantics, and private-preserves-collaborators behavior. These are non-obvious policy facts an agent could not infer from 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?

Purpose is front-loaded in the first clause, then supporting policy detail follows in dense, mostly waste-free sentences. It is on the long side, but each clause adds a distinct constraint rather than restating the schema.

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?

For a multi-modal mutation tool (grant, revoke, visibility) with no annotations, the description supplies authorization rules, role semantics, actorId format, and the visibility alternative; an output schema exists so return values need no explanation. Nothing essential to correct invocation is missing.

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 already 88%, so the baseline is 3; the description adds real value by decoding actorId ('github:<login>', 'operator', 'agent:<fingerprint>') and explaining role/visibility semantics and the actorId-vs-visibility choice. It does not cover token/agentName/agentModel, but those are well documented in 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?

States a specific verb+resource ('Share a design ... or take that sharing back') and immediately distinguishes itself from the sibling that reads access (ui_builder_design_access), which it explicitly names. An agent can tell this is the mutation counterpart to the read-only access listing.

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?

Gives explicit conditions: use actorId to grant/revoke a specific party, or pass visibility to flip private/public, with 'Private keeps existing invited collaborators'. It also states the authorization precondition ('Only the design's owner may share it') and the agent-grant case, which is exactly when-to-use guidance.

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.