Skip to main content
Glama
Hermoso

Hermoso

Official

Plan a video ad from a product link

click_to_ad

Paste a product page link to plan a creator-style video ad: it reads product details, saves the item to your catalog, pins the page's real photo, and prepares the concept.

Instructions

Paste a product page link (Shopify, Amazon or any store page) and get a creator-style video ad planned for that product. Hermoso reads the page (name, photos, what it says about the product, price), saves the product to the brand's catalog, checks the page's real product photo and pins it to this ad (the brand's saved default photo is not changed), then plans the ad. A store that hides its page from servers is read in a real browser; failing that the name comes from the link and the photo from a search, and the reply says so. Nothing renders here: show the user the concept, then call render_ad with the returned creative (dryRun:true first for the exact price). Works with or without a saved brand.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "click_to_ad"
  }
}

Input Schema

NameRequiredDescriptionDefault
sayNowhat the creator should say, or the angle, in the user's words
urlYesthe product page link, https://…
styleNougc_selfie (talking to camera, default), ugc_unboxing, ugc_demo (how-to), ugc_tryon (try-on or haul), ugc_product (product close-ups, no face), ugc_shopping (in-store find), ugc_delivery, transformation (before and after), day_in_life (at home), grwm (get ready with me), ugc_addiction (obsessed with it)
get_costNotrue: return the price only; nothing runs or bills
languageNolanguage for the script and copy, default English
durationSecondsNolength in seconds, 4-180; default 15
idempotency_keyNochosen once, resent unchanged on retries: the same key never buys twice
expected_creditsNothe get_cost price; refused unbilled if the live price differs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.532
    • addedInput schema / properties / expected_credits
      Added value: +{
      +  "description": "the get_cost price; refused unbilled if the live price differs",
      +  "type": "number"
      +}
    • addedInput schema / properties / get_cost
      Added value: +{
      +  "description": "true: return the price only; nothing runs or bills",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "chosen once, resent unchanged on retries: the same key never buys twice",
      +  "type": "string"
      +}
  2. Addedv0.1.454

TDQS

A4.6/5.0
Behavior5/5

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

Beyond readOnlyHint=false and destructiveHint=false, the description discloses the actual side effects: the product is saved to the brand's catalog and its photo pinned to this ad, explicitly without changing the brand's saved default photo, which confirms the non-destructive framing. It also discloses fallback behavior for stores that hide pages from servers (real browser, then link-derived name and searched photo, with the reply saying so), which the annotations cannot express.

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 purpose, then side effects, then fallbacks, then the required next step — a logical order with no filler sentences. It is dense and slightly run-on in the middle clause about browser fallback, but every sentence 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 an 8-parameter open-world tool with no output schema, the description covers the gaps that matter: side effects on the brand catalog, photo-pinning semantics, degraded-page fallbacks, and the hand-off to render_ad. An agent has enough to call it correctly and to tell the user what happened afterwards.

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 coverage is 100% and each of the 8 parameters carries its own description, so the schema does the heavy lifting and a 3 is the baseline. The description adds no parameter-level detail of its own — the dryRun:true mention refers to render_ad, not to this tool's get_cost or expected_credits flow.

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 first sentence states a specific verb (plan) and resource (creator-style video ad) plus the exact input (a product page link from Shopify, Amazon or any store). It names the boundary against render_ad — planning only, nothing renders — so an agent can distinguish it from its closest sibling without reading either 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?

It gives explicit when-to-use (user pastes a product link), when-not (nothing renders here), and the exact follow-up sequence: show the concept, then call render_ad with the returned creative, dryRun:true first for price. The get_cost parameter and the 'works with or without a saved brand' note remove the remaining selection doubt.

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