Skip to main content
Glama

Compose Preview Catalogs

by io.github.yschimke
OverviewDiscussionsAdmin

ui_builder_set_implementation

Record the pull request that implements a design: its URL, its status (draft, open, merged, closed), the design revision it implements, and — once you have compared the PR's rendered previews with the design — previewMatch {status: match|mismatch|unknown, evidence: a URL to the comparison, note}. Replaces the whole record; pass only designId to clear it. Writing the same record again changes nothing and wakes nobody. Needs write access to the design.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
prNoThe pull request URL.
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.
statusNoDefaults to open.
designIdYes
revisionNoThe design revision the PR implements.
agentNameNoOptional agent/client name shown to design viewers; self-reported.
agentModelNoOptional current model name shown to design viewers; self-reported. Omit when unknown.
previewMatchNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • 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"
+}
  2. Added

TDQS

A4/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers: full-replace semantics ('Replaces the whole record'), the clear path, idempotency ('writing the same record again changes nothing and wakes nobody'), and an explicit permission requirement ('Needs write access to the design'). These are exactly the non-obvious mutation traits an agent needs before calling.

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 the sentences are dense but each earns its place (replace semantics, idempotency, permission). The long opening sentence packs several concepts together, which slightly hurts scanability but wastes no words.

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?

An output schema exists, so return values need no explanation, and the description supplies the mutation semantics, clearing behavior, and auth requirement an agent needs. The token/poll_access integration is left entirely to the schema, which is acceptable but a minor omission.

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 75%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains the previewMatch object's intent and when to populate it, and specifies that only designId should be passed to clear the record. It does not cover the token/poll_access flow, which the schema handles.

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?

States a specific verb and resource ('Record the pull request that implements a design') and enumerates the fields being recorded. An agent can distinguish this write from the read-oriented sibling ui_builder_implementation_status, though neither sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides condition-based guidance for one field ('once you have compared the PR's rendered previews with the design') and explains the clearing case ('pass only designId to clear it'). It never states when to reach for this tool versus ui_builder_implementation_status or ui_builder_find_design_for_pr, so tool selection is left to inference.

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
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.

Resources