Skip to main content
Glama
hermoso-ai

Hermoso

Official

Set product photo

set_product_image
Idempotent

Lock a product photo as your brand's default so future ad renders use the true packaging. Validates the image, rejects unsafe/off-category shots, saves a durable URL, and confirms what the brand holds.

Instructions

Lock an image as the ad's real PRODUCT photo and SAVE it as this brand's default product, so every later plan_ad / render_ad / generate_image grounds on the true packaging without being told again. Pass imageUrl = a product shot's URL — an image from a prior research result (an organic Instagram/TikTok post, a scraped page image), a workspace / list_product_photos url, or any public product photo. The server downloads it and runs a product+safety check: a lifestyle/scene shot with no clear product, or an off-category / unsafe image, is REJECTED and NOTHING is locked or saved (the summary says why). On PASS it persists the photo to a DURABLE url, writes it to the brand's product library as the DEFAULT, and READS THE BRAND BACK to confirm — savedToBrand and the summary report what the brand ACTUALLY holds now, never what was asked for, so if it did not become the default you are told instead of finding out from a paid render. Bills one vision check. Reads YOUR saved brand for the category match (pass brandId to target a specific brand — switches this key's active brand like use_brand).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
brandIdNoa brand id/name from list_brands to lock the product for; omit to use the active brand
imageUrlYesthe image URL to lock as the product (from a research result, a workspace / list_product_photos url, or any public product photo)
source_noteNoa short note on where it came from, e.g. "from their IG post"
Install Server

TDQS

A4.7/5.0
Behavior5/5

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

Adds substantial context well beyond the annotations: the server downloads and validates, bills one vision check, persists to a durable URL, reads the brand back to confirm, and reports what the brand ACTUALLY holds rather than what was requested. This far exceeds the bare readOnlyHint=false / idempotentHint=true / openWorldHint=true annotations and gives the agent accurate expectations for a mutating, costly operation.

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?

Long, but dense and justified for the tool's complexity — it covers purpose, failure semantics, confirmation behavior, cost, and cross-tool effects. Core purpose is front-loaded in the first sentence. It reads as verbose rather than bloated, though it could trim the redundant phrasing around 'never what was asked for.'

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?

No output schema exists, so the description carries the return-value burden — and it does, referencing `savedToBrand` and a summary that reports actual brand state. Combined with side-effect and cost disclosure, an agent has nearly everything needed. Minor gaps: exact response shape and failure-status codes are not specified, but the summary semantics largely compensate.

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 baseline is 3, but the description adds real value: it specifies imageUrl is a product shot (excluding lifestyle shots), explains the consequence of the validation (rejection means nothing is locked/saved), and clarifies that brandId switches the active brand. This goes beyond the schema's terse field notes.

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 specific verb+resource ('Lock an image as the ad's real PRODUCT photo and SAVE it as this brand's default product') and immediately distinguishes itself by explaining the downstream effect on plan_ad / render_ad / generate_image. The agent knows exactly what this does and how it differs from the many adjacent ad/asset tools.

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 enumerates acceptable image sources (prior research results, workspace / list_product_photos URLs, any public photo), names the affected downstream tools, and explains the brandId behavior via the use_brand analogy. It also states rejection conditions (lifestyle/scene shot, off-category, unsafe), telling the agent both when to use it and what will fail.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hermoso-ai/hermoso'

If you have feedback or need assistance with the MCP directory API, please join our Discord server