Claude GenUI

Render card

render_card

Renders structured information cards inline in chat, such as weather, profiles, summaries, and checklists, with optional action buttons that send follow-up prompts to Claude.

Instructions

Render a structured information card inline (e.g. weather, product, profile, summary, checklist, comparison). Optional action buttons send a follow-up prompt back to Claude when clicked.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "title": "<title>"
    },
    "name": "render_card"
  }
}

Input Schema

Name	Required	Description
`hero`	No	One big headline number, e.g. {value:'23°C', caption:'Feels like 25°C'}
`icon`	No	A single emoji shown beside the title
`badge`	No	Short status tag, e.g. 'New', 'In stock'
`image`	No	https image URL
`items`	No	Checklist / bullet list
`title`	Yes
`fields`	No	Key/value grid
`actions`	No
`subtitle`	No
`description`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 15, 2026

TDQS

A3.6/5.0

Behavior3/5

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

No annotations are supplied, so the description carries the behavioral burden. It usefully discloses that action buttons send a follow-up prompt back to Claude on click, which is real interaction behavior beyond the schema. It says nothing about whether cards are ephemeral, how many can be rendered, or any size or content limits.

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

Conciseness5/5

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

Two sentences, no filler, with the core capability front-loaded before the interaction detail. Every clause earns its place.

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 10-parameter nested rendering tool with no output schema and no annotations, the definition covers purpose, content types, and the one non-obvious behavior (click-to-prompt). The remaining gap is routing guidance against render_chart and render_html.

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 60% across 10 parameters, with the nested structures (hero, items, fields, actions) reasonably documented in the schema itself. The description adds meaning only for actions, explaining the round-trip prompt behavior; title, subtitle, and description remain unexplained in both places.

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 ('Render a structured information card inline') and backs it with concrete content examples (weather, product, profile, checklist, comparison) that separate it in spirit from chart or HTML rendering. It never names the siblings render_chart or render_html, so the differentiation is inferred from the word 'card' rather than stated.

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?

The enumerated examples imply when a card is the right surface, but there is no explicit when-not guidance and no pointer to render_chart or render_html for chart or free-form HTML output. An agent must infer the boundary from the tool names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server