Skip to main content
Glama

Export brand guide

brand_export
Idempotent

Exports the compiled brand system into portable native formats for AI chats, code editors, team guidelines, CSS, Tailwind, and PDFs. Use after compiling to share or embed a consistent brand wherever needed.

Instructions

Bundle the compiled brand system into a portable artifact in a destination's native format. Use when asked 'share my brand', 'export for ChatGPT/Cursor/Codex/team', 'add the brand to AGENTS.md', 'Cursor rules', 'CSS variables', 'Tailwind theme', 'shadcn theme', 'generate brand guidelines', or 'create a brand PDF'. Targets: 'chat' (markdown for any AI conversation), 'code' (MCP config + CLAUDE.md snippet), 'team' (human guidelines), 'email' (~500-word summary), 'claude-skill' (SKILL.md with embedded logo), 'pdf' (branded guide), 'agents-md' (AGENTS.md section), 'cursor-rules' (.cursor/rules/brand.mdc), 'css-variables' (:root --brand-* + dark block), 'tailwind' (v4 @theme CSS), 'shadcn' (shadcn/ui :root/.dark variables). CSS targets are generated from the compiled DTCG tokens. Writes to .brand/exports/ and returns the full content (text targets) or a generation summary (pdf). Requires brand_compile to have run first. NOT for previewing one section — use brand_preview.

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": {
      "target": "<target>"
    },
    "name": "brand_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetYesWhere this export will be used — pick the host's native format. 'chat': upload to AI conversation (Claude/ChatGPT/Gemini). 'code': MCP config + CLAUDE.md snippet. 'team': share with designers/writers. 'email': send via Slack or email. 'claude-skill': persistent Claude skill file with embedded logo + brand rules. 'pdf': brand guide PDF with swatches, type, rules, voice. 'agents-md': AGENTS.md section for Codex/Cursor/any AGENTS.md-reading agent. 'cursor-rules': .cursor/rules/brand.mdc (auto-attached to UI files). 'css-variables': :root { --brand-* } custom properties with a dark-theme block. 'tailwind': Tailwind CSS v4 @theme { --color-brand-*, --font-brand-* }. 'shadcn': shadcn/ui :root + .dark theme variables (--primary, --background, --ring, --radius ...). Example: 'tailwind'.
include_logoNoEmbed logo SVG/data URI in the export. Set false to reduce file size. Default: true.

Output Schema

NameRequiredDescriptionDefault
_metadataYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.18.0
    • changedInput schema / properties / target / description
      Previous value: -"Where this export will be used. 'chat': upload to AI conversation (Claude/ChatGPT/Gemini). 'code': paste into CLAUDE.md or .cursorrules. 'team': share with designers/writers. 'email': send via Slack or email. 'claude-skill': persistent Claude skill file with embedded logo + brand rules. 'pdf': brand guide PDF with color swatches, typography, visual rules, and voice summary — no browser needed."New value: +"Where this export will be used — pick the host's native format. 'chat': upload to AI conversation (Claude/ChatGPT/Gemini). 'code': MCP config + CLAUDE.md snippet. 'team': share with designers/writers. 'email': send via Slack or email. 'claude-skill': persistent Claude skill file with embedded logo + brand rules. 'pdf': brand guide PDF with swatches, type, rules, voice. 'agents-md': AGENTS.md section for Codex/Cursor/any AGENTS.md-reading agent. 'cursor-rules': .cursor/rules/brand.mdc (auto-attached to UI files). 'css-variables': :root { --brand-* } custom properties with a dark-theme block. 'tailwind': Tailwind CSS v4 @theme { --color-brand-*, --font-brand-* }. 'shadcn': shadcn/ui :root + .dark theme variables (--primary, --background, --ring, --radius ...). Example: 'tailwind'."
    • changedInput schema / properties / target / enum
      Previous value: -[
      -  "chat",
      -  "code",
      -  "team",
      -  "email",
      -  "claude-skill",
      -  "pdf"
      -]New value: +[
      +  "chat",
      +  "code",
      +  "team",
      +  "email",
      +  "claude-skill",
      +  "pdf",
      +  "agents-md",
      +  "cursor-rules",
      +  "css-variables",
      +  "tailwind",
      +  "shadcn"
      +]
  2. Addedv0.17.0
  3. Removedv0.13.4
  4. Changed1 schema field changedv0.11.0
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": true,
      +  "properties": {
      +    "_metadata": {
      +      "additionalProperties": true,
      +      "properties": {
      +        "next_steps": {
      +          "items": {
      +            "type": "string"
      +          },
      +          "type": "array"
      +        },
      +        "what_happened": {
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "what_happened",
      +        "next_steps"
      +      ],
      +      "type": "object"
      +    }
      +  },
      +  "required": [
      +    "_metadata"
      +  ],
      +  "type": "object"
      +}
  5. Changed2 schema fields changedv0.9.2
    • changedInput schema / properties / target / description
      Previous value: -"Where this export will be used. 'chat': upload to AI conversation (Claude/ChatGPT/Gemini). 'code': paste into CLAUDE.md or .cursorrules. 'team': share with designers/writers. 'email': send via Slack or email. 'claude-skill': persistent Claude skill file with embedded logo + brand rules — the gold standard for automatic brand application in every artifact."New value: +"Where this export will be used. 'chat': upload to AI conversation (Claude/ChatGPT/Gemini). 'code': paste into CLAUDE.md or .cursorrules. 'team': share with designers/writers. 'email': send via Slack or email. 'claude-skill': persistent Claude skill file with embedded logo + brand rules. 'pdf': brand guide PDF with color swatches, typography, visual rules, and voice summary — no browser needed."
    • changedInput schema / properties / target / enum
      Previous value: -[
      -  "chat",
      -  "code",
      -  "team",
      -  "email",
      -  "claude-skill"
      -]New value: +[
      +  "chat",
      +  "code",
      +  "team",
      +  "email",
      +  "claude-skill",
      +  "pdf"
      +]
  6. First observedv0.5.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare idempotent=true, destructive=false, openWorldHint=false, so the safety profile is covered; the description adds the meaningful extras: it writes files to .brand/exports/<file> and returns either full content (text targets) or a generation summary (pdf). What it does not say is how it behaves when an export file already exists (overwrite vs. error), which is the one remaining behavioral gap.

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?

Front-loaded with purpose, triggers, and exclusions, which is good structure. But the 11-target enumeration is listed twice in effect (once inline, once in the schema enum descriptions), and several entries restate the schema verbatim, inflating length without adding selection value.

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 one-required-param tool with a full output schema, the description covers prerequisites, output destination, return shape, and alternative routing. An agent has everything needed to call it correctly on the first attempt.

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 coverage is 100% and the enum descriptions already explain every target, so the baseline of 3 applies. The description largely reproduces the same target list rather than adding new semantics, adding only one genuinely new fact: CSS targets are generated from the compiled DTCG tokens.

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 and resource ('Bundle the compiled brand system into a portable artifact in a destination's native format') and enumerates the concrete target formats, which makes it instantly distinguishable from brand_compile, brand_report, and brand_context. It also explicitly names a non-overlapping sibling (brand_preview) for the adjacent use case.

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 trigger phrases ('share my brand', 'Cursor rules', 'create a brand PDF'), a clear negative boundary ('NOT for previewing one section — use brand_preview'), and a hard prerequisite ('Requires brand_compile to have run first'). Nothing about when to select this tool 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.