Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Plan ad variations

plan_variations

Fan a brief into multiple distinct ad angles—different hooks, mechanics, or audiences—each with its own headline and visual brief. Plan variants before rendering and scoring to focus ad tests.

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.

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
Behavior5/5

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

The description adds substantial behavioral context beyond the annotations: it is a planning-only operation, it produces multiple variants, and it does not render output itself. The 'renders nothing itself' clause prevents a common misinvocation where the agent expects image/video output from this tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence conveys the core operation, output structure, downstream tool usage, and a key behavioral caveat without wasted words. The most important differentiator ('LLM planning only; renders nothing itself') is placed at the end but still present.

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 planning tool with no output schema, the description provides enough to understand what the tool returns conceptually: N variants, each with headline and visual brief. The schema covers all parameters, and the description covers behavior, output shape, and downstream workflow, so nothing critical is missing.

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 all four parameters. The description adds the 'N' semantics tied to count and the notion of 'brief' tied to product, but it does not elaborate on brand or language. This meets the baseline for full schema coverage without adding significant new parameter meaning.

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 names a specific verb ('Fan'), a resource ('a brief'), and a precise output ('N DISTINCT ad angles... each with its own headline + visual brief'). It also differentiates from rendering tools by stating 'LLM planning only; renders nothing itself' and explicitly routes output to generate_image and score_ad.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The description implies the tool is for generating multiple distinct ad angles rather than a single ad, but it never explicitly states when to choose this over closely related siblings like plan_ad, mine_angles, or multiply_ad. It does clarify that this tool does not render anything, which is a useful exclusion, but alternative-selection guidance 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.

Deploy Server

Other Tools