Skip to main content
Glama
Hermoso

Hermoso

Official

Update profile fields

update_brand
Destructive

Patch specific fields of the active brand profile—voice, audience, fonts, palette, and more—without overwriting saved values. Change one brand detail while keeping the rest intact.

Instructions

Patch SPECIFIC fields of the active profile (name, domain, sells, summary, category, audience, positioning, voice, style, goal, fonts, palette, logos, brand/product name pronunciations, profileType: explore = kept but unused) WITHOUT overwriting the rest — a read-modify-write on the saved brand. Use for “change our voice to playful”, “we sell to dentists now”, “our fonts are Benne and Josefin Sans”, “our colours are #3D4C41 and #EEE4DA”. The fonts and palette are what template ads are set in and what every planned ad is told to use, so set them here rather than describing them in style. To onboard a brand from scratch, use draft_brand. If no brand is saved yet and you only INFERRED one from what the user is making, ask them to confirm it is their brand before saving it (they may be working for a client or just trying things). Only pass the fields you’re changing.

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": "update_brand"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNocurrent marketing goal
logoNologo image: URL or local file path to a PNG, JPEG or WebP (no SVG)
nameNobrand name
brandNoprofile id/name from list_brands, this call only
fontsNothe brand fonts, any family name: a list with the HEADLINE font first and the BODY font second (it replaces the saved list), or {headline, body} to change one and keep the other ("" removes one). Template ads load any Google Fonts family; the reply says what each will be set in.
sellsNowhat the brand sells
styleNovisual style — palette, typography, aesthetic
voiceNobrand voice/tone
domainNowebsite domain
paletteNothe brand colours as six-digit hex codes like "#3D4C41", in order, up to 8. Replaces the saved palette; [] clears it. A short code (#abc) or one without # is refused, never rewritten.
summaryNoone-line description
audienceNowho the brand sells to, one line
categoryNoproduct or business category, one line
logoDarkNofor light pictures
logoLightNofor dark pictures; "none" removes
pronounceNohow the brand NAME is said aloud, as a simple respelling with the stressed syllable in capitals (e.g. "KOH-dee-ak"). Videos use it as a delivery note beside the spoken line; set it when a render mispronounced the name.
positioningNohow the brand is positioned against alternatives, one line
profileTypeNowebsite, social, describe or explore; explore keeps the profile but stops using it
pronunciationsNohow PRODUCT names are said aloud, e.g. {"Power Cakes": "POW-er cakes"}. Merged into the saved ones; an empty string removes one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.539
    • addedInput schema / properties / fonts
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "properties": {
      +        "body": {
      +          "type": "string"
      +        },
      +        "headline": {
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    }
      +  ],
      +  "description": "the brand fonts, any family name: a list with the HEADLINE font first and the BODY font second (it replaces the saved list), or {headline, body} to change one and keep the other (\"\" removes one). Template ads load any Google Fonts family; the reply says what each will be set in."
      +}
    • addedInput schema / properties / palette
      Added value: +{
      +  "description": "the brand colours as six-digit hex codes like \"#3D4C41\", in order, up to 8. Replaces the saved palette; [] clears it. A short code (#abc) or one without # is refused, never rewritten.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. Changed6 schema fields changedv0.1.465
    • addedInput schema / properties / audience / description
      Added value: +"who the brand sells to, one line"
    • addedInput schema / properties / category / description
      Added value: +"product or business category, one line"
    • addedInput schema / properties / logo / description
      Added value: +"logo image: URL or local file path to a PNG, JPEG or WebP (no SVG)"
    • addedInput schema / properties / name / description
      Added value: +"brand name"
    • addedInput schema / properties / positioning / description
      Added value: +"how the brand is positioned against alternatives, one line"
    • addedInput schema / properties / profileType / description
      Added value: +"website, social, describe or explore; explore keeps the profile but stops using it"
  3. Changed1 schema field changedv0.1.409
    • addedInput schema / properties / profileType
      Added value: +{
      +  "enum": [
      +    "website",
      +    "social",
      +    "describe",
      +    "explore"
      +  ],
      +  "type": "string"
      +}
  4. Changed3 schema fields changedv0.1.398
    • addedInput schema / properties / logo
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / logoDark
      Added value: +{
      +  "description": "for light pictures",
      +  "type": "string"
      +}
    • addedInput schema / properties / logoLight
      Added value: +{
      +  "description": "for dark pictures; \"none\" removes",
      +  "type": "string"
      +}
  5. Changed1 schema field changedv0.1.374
    • changedInput schema / properties / brand / description
      Previous value: -"brand id/name from list_brands, this call only"New value: +"profile id/name from list_brands, this call only"
  6. Changed1 schema field changedv0.1.371
    • addedInput schema / properties / brand
      Added value: +{
      +  "description": "brand id/name from list_brands, this call only",
      +  "type": "string"
      +}
  7. Changed2 schema fields changedv0.1.366
    • addedInput schema / properties / pronounce
      Added value: +{
      +  "description": "how the brand NAME is said aloud, as a simple respelling with the stressed syllable in capitals (e.g. \"KOH-dee-ak\"). Videos use it as a delivery note beside the spoken line; set it when a render mispronounced the name.",
      +  "type": "string"
      +}
    • addedInput schema / properties / pronunciations
      Added value: +{
      +  "additionalProperties": {
      +    "type": "string"
      +  },
      +  "description": "how PRODUCT names are said aloud, e.g. {\"Power Cakes\": \"POW-er cakes\"}. Merged into the saved ones; an empty string removes one.",
      +  "propertyNames": {
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
  8. Addedv0.1.161

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already flag this as a destructive, non-idempotent mutation, and the description goes further by spelling out patch semantics (read-modify-write, the rest is untouched) and what actually gets replaced or cleared ('[] clears it', fonts list replaces the saved list). It adds real context the annotations cannot express, so there is no contradiction with destructiveHint=true.

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?

The partial-update constraint and the field list are front-loaded, and most sentences carry unique information. A few clauses are denser than needed ('so set them here rather than describing them in style'), but nothing is padding.

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 19-parameter destructive mutation with no output schema, the description covers the essentials: partial-update semantics, replacement/clear behavior for fonts and palette, the onboarding alternative, and the confirmation step for inferred brands. The only omissions, auth requirements and return shape, are minor here.

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?

With 100% schema description coverage, the schema already documents every parameter, including the fonts list-versus-object forms and palette hex rules. The description adds a useful global rule ('Only pass the fields you're changing') and a field list, but no per-parameter meaning beyond the schema, so baseline 3 applies.

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?

The description states a specific verb and resource ('Patch SPECIFIC fields of the active profile') and names the exact fields covered, so an agent can tell what it touches without opening the schema. It also draws a clear line against 'draft_brand' for from-scratch onboarding.

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?

It gives concrete trigger phrases ('change our voice to playful', 'our fonts are Benne and Josefin Sans'), names the alternative for onboarding ('use draft_brand'), and adds a when-not precondition: if only an inferred brand exists, ask the user to confirm before saving. Guidance is explicit rather than inferable.

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

Deploy Server

Other Tools