Skip to main content
Glama

Save email look

brand_set_theme
Idempotent

Saves the default look of every email: theme colors (background, surface, text), buttons (button_style solid or outline, button_shape pill or rounded) and the info bar, a dark band across the top (for example free shipping). A single campaign can override any of these with blocks.theme and blocks.info_bar. Fields you leave out stay as they are; info_bar: null removes the bar; a color "" goes back to the default. Text needs 4.5:1 contrast with the surface; campaign_preview warns when it does not. Uses no quota and sends nothing. Only save what the person approved. Example: {"theme": {"surface": "#ffffff", "text": "#27272a", "button_style": "outline", "button_shape": "pill"}, "info_bar": {"text": "Free shipping on orders over $99", "url": "https://shop.example/shipping"}} Requires API key scope: draft.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "brand_set_theme"
  }
}

Input Schema

NameRequiredDescriptionDefault
themeNo
info_barNoDefault info bar for every email, or null to remove it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Well beyond the annotations, the description discloses merge semantics (omitted fields stay as they are), two distinct reset mechanisms (info_bar: null removes the bar; a color "" returns to default), a validation rule (4.5:1 contrast against surface) and the sibling that surfaces violations (campaign_preview). It also covers side-effect profile ('Uses no quota and sends nothing') and auth scope ('Requires API key scope: draft'), consistent with readOnlyHint=false and destructiveHint=false.

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?

Front-loaded with what is saved, then edge cases, then guardrails and the example — a sensible order with dense, low-waste sentences. It runs long with a full JSON example, but every clause (reset rules, contrast rule, quota, scope) carries information an agent needs.

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 two-parameter nested-object mutation with no output schema, the definition covers merge behavior, required auth scope, cost, validation constraints, and a concrete payload example. Nothing material to correct invocation is missing; return value detail is unnecessary absent an output schema.

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 description coverage is only 50%, and the description compensates by explaining intent and edge cases the schema does not: what the info bar is (a dark band across the top, e.g. free shipping), the allowed button_style/button_shape values, the null and empty-string reset semantics, and a full worked example. It does not restate the color pattern or url maxLength, but those are already 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 and resource: saves the DEFAULT look of every email, enumerating what that covers (theme colors, buttons, info bar). It draws a clear boundary against per-campaign overrides via blocks.theme/blocks.info_bar, so an agent can distinguish this from campaign editing tools without opening the schema.

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?

Gives the key alternative explicitly — a single campaign can override any of these with blocks.theme and blocks.info_bar, which routes the agent away from this tool when the change is campaign-scoped. Also states the constraint 'Only save what the person approved' and that it sends nothing, but does not explicitly say when this should be called (e.g., initial brand setup vs. later revision) or mention brand_get for reading current values.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources