Skip to main content
Glama

Compose Preview Catalogs

by io.github.yschimke
OverviewDiscussionsAdmin

catalog_render_preview

Render one preview. Like local compose-ai-tools, the default semantics observation is token-frugal; request observe=png for pixels, observe=svg for the compose/figma-svg vector export as SVG source, or observe=scroll-png / observe=scroll-svg for the full-page capture of a scrollable screen rather than the viewport crop. This made-to-order lane requires live grant scope. Use resources/read for the published snapshot lane.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uriNo
tokenNoA 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.
catalogNo
observeNo
overridesNo
previewIdNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
imageUrlNoShort-lived signed https URL of the rendered PNG, on a host with a public origin.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "imageUrl": {
+      "description": "Short-lived signed https URL of the rendered PNG, on a host with a public origin.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries full burden. It discloses the auth requirement (live grant scope), the default behavior (semantics observation is token-frugal), and the output shape of each observe mode (pixels, SVG source, full-page scroll capture). It does not state reversibility, rate limits, or failure modes, so the behavioral picture is partial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core render/observe information is front-loaded, but the prose is heavy with internal jargon ('made-to-order lane', 'token-frugal', 'like local compose-ai-tools') that adds opaqueness rather than signal. It is information-dense but not efficiently worded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the lane/auth context is present. However, with 6 parameters at two required-sets and only 17% schema coverage, the description leaves key identifiers (uri vs catalog+previewId, token) unaddressed, so an agent still lacks enough to invoke confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 17%, so the description must compensate. It explains 4 of the 6 observe enum values (png, svg, scroll-png, scroll-svg) and implies the default is semantics, but leaves 'hash' undefined and gives no meaning for uri, catalog, or previewId, which appear in the anyOf requirement.

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?

The opening 'Render one preview' states a specific verb and resource, and the observe-mode enumeration clarifies what kind of render is produced. It does not, however, differentiate itself from sibling renderers like catalog_render_matrix or ui_builder_render_native.

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 selection guidance for the observe values and names an alternative lane ('Use resources/read for the published snapshot lane'), plus a precondition ('requires live grant scope'). It stops short of stating when NOT to use this tool versus the closely-named catalog siblings, but the lane routing and mode selection are explicit.

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 toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources