Skip to main content
Glama
Hermoso

Hermoso

Official

Change app settings

update_settings
DestructiveIdempotent

Change account-wide app settings such as ad language, theme, weekly competitor-watch email, and email notification groups; only pass the settings you want to update.

Instructions

Change this account's app settings. language = the language EVERY ad, script and plan is written in from now on (chat replies follow the language the user writes in) (say the language in plain English, e.g. "German", "Japanese", "Brazilian Portuguese") — it applies to renders made over MCP as well as in the app. theme = the app's appearance, "dark" or "light". watchEmail = the weekly competitor-watch email on/off. emails = turn Hermoso emails on or off by group, including turning back on what an unsubscribe link turned off. Only pass what you are changing. Account-wide (every profile), and it takes effect on the next call.

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_settings"
  }
}

Input Schema

NameRequiredDescriptionDefault
themeNoapp appearance
emailsNoemail switches by group; pass only the ones you are changing
languageNolanguage for generated ads and copy (chat replies follow the language the user writes in) — e.g. "English", "German", "Japanese"
watchEmailNoweekly competitor-watch email on/off

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.539
    • addedInput schema / properties / emails
      Added value: +{
      +  "description": "email switches by group; pass only the ones you are changing",
      +  "properties": {
      +    "all": {
      +      "description": "master switch; off = only sign-in and billing emails arrive",
      +      "type": "boolean"
      +    },
      +    "autopilot": {
      +      "description": "posts ready for review",
      +      "type": "boolean"
      +    },
      +    "notices": {
      +      "description": "low-credit and plan notices",
      +      "type": "boolean"
      +    },
      +    "productNews": {
      +      "description": "product news and launches",
      +      "type": "boolean"
      +    },
      +    "tips": {
      +      "description": "tips and how-tos after signup",
      +      "type": "boolean"
      +    },
      +    "watch": {
      +      "description": "weekly competitor-watch email",
      +      "type": "boolean"
      +    },
      +    "weeklyPosts": {
      +      "description": "weekly email about your posts",
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed1 schema field changedv0.1.454
    • changedInput schema / properties / language / description
      Previous value: -"language for generated ads, copy and answers — e.g. \"English\", \"German\", \"Japanese\""New value: +"language for generated ads and copy (chat replies follow the language the user writes in) — e.g. \"English\", \"German\", \"Japanese\""
  3. Addedv0.1.161

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known; the description adds context the annotations cannot — that changes are account-wide across every profile, that the language applies to MCP renders as well as in-app, and that emails can re-enable groups an unsubscribe link turned off. It never explains what is not reversible or how a language switch affects already-generated assets beyond "from now on."

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 each parameter is labeled, so an agent can scan to the field it needs. The language clause is the longest sentence and partly restates the schema's own language description, which is the only real redundancy.

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 four-parameter mutation tool with a nested emails object and no output schema, the description covers scope, partial-passing semantics, per-field meaning, and effect timing — enough to call it correctly. It doesn't mention permissions or what the response indicates, but neither is critical for a settings setter.

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 100%, so the baseline is 3, and the description earns above that by clarifying behavior the schema leaves implicit: the language value should be a plain-English name ("German", "Brazilian Portuguese"), it does not govern chat reply language, and emails accepts partial group objects. Theme and watchEmail get no elaboration beyond what the schema already states.

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?

The description opens with a specific verb+resource ("Change this account's app settings") and enumerates the four settings it touches, which cleanly separates it from the read-only sibling get_settings. It stops short of naming the read/write pairing explicitly, so differentiation is inferred from the verb 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 Guidelines4/5

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

"Only pass what you are changing" establishes partial-update semantics, and "Account-wide (every profile), and it takes effect on the next call" tells the agent the blast radius and timing. What's missing is an explicit pointer to get_settings for reading current values before a change, which would have made routing unambiguous.

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