Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Plan ad variations

plan_variations

Generate distinct ad angles from a product brief, each with a headline and visual brief, so you can render and score multiple variations.

Instructions

Fan a brief into N DISTINCT ad angles (different hooks/mechanics/audiences), each with its own headline + visual brief — then render each with generate_image and rank with score_ad. LLM planning only; renders nothing itself. To plan AND render a batch of finished static ads for one or several products in one call (up to 20 per product), use make_static_ads.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
brandNobrand name or profile object; OMIT to use the workspace’s saved brand
countNohow many distinct variants (default 6)
productYeswhat to advertise
languageNooutput language for the variant copy (e.g. Spanish) — default English

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.161
    • changedOutput schema / (root)
      Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "angles": {
-      "description": "alternate key the planner may return the variants under",
-      "items": {},
-      "type": "array"
-    },
-    "variants": {
-      "description": "the distinct ad angles ({name, hook, headline, visual brief})",
-      "items": {},
-      "type": "array"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false. The description adds the important boundary that this is a planning step only and renders nothing itself, which disambiguates the otherwise confusing mention of generate_image/score_ad. It does not cover whether the plan is persisted or whether downstream renders cost credits, so it stops short of full transparency.

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 the core action and output, then the workflow, then the exclusion. Two sentences plus a clause with little waste, though the generate_image/score_ad workflow mention adds slight density that then has to be walked back with 'renders nothing itself.'

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?

With no output schema, the description carries the return-value burden and does so by naming the per-angle artifacts (headline + visual brief). For a 4-param, low-complexity planning tool this is nearly complete; only the persistence/shape of the returned plan is left implicit.

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 100%, so the schema already documents brand, count, product, and language. The description only echoes the 'N DISTINCT' notion of count and the brief concept; it adds no format or default guidance beyond what the schema provides. Baseline 3 is appropriate.

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 precise verb and output ('fan a brief into N DISTINCT ad angles ... each with its own headline + visual brief'), and explicitly names the siblings it works with (generate_image, score_ad) and the one it is not (make_static_ads). An agent can distinguish it from plan_ad, headline_variants, and make_static_ads without opening any schema.

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?

Explicitly routes the agent: 'To plan AND render a batch of finished static ads ... use make_static_ads', and clarifies its own boundary with 'LLM planning only; renders nothing itself.' Both the when-to-use and the when-to-use-something-else are stated.

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