Skip to main content
Glama

Generate AI product photos

generate_photos

Queue a set of AI photos for one catalog product. Formats and credit cost: photo_model (9, a photoshoot with an AI model wearing or using the product), photo_product (8, clean studio and lifestyle product shots), photo_infographic (7, a labelled infographic built only from the product's real facts, needs enough facts on the product page). A set renders in a few minutes; every image comes in a square (2000x2000) and a portrait (1080x1350) size, plus a zip of the whole set. Credits are charged from the account; a failed set refunds automatically. Poll list_photo_sets for download links.

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": {
      "product_id": "<product_id>",
      "format": "<format>"
    },
    "name": "generate_photos"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatYes
product_idYesProduct id from list_products

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Beyond annotations it discloses credit costs, a refund-on-failure policy, expected render time, and the exact output artifacts (square 2000x2000, portrait 1080x1350, plus a zip of the set) — substantial context the annotations do not carry. The one gap for a non-idempotent, credit-charging queue operation is that it never warns against retrying or re-queuing a set that may already be in flight, which is the main way an agent would burn credits.

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?

The action and the format/credit breakdown are front-loaded, and the operational facts (render time, artifact sizes, refunds, polling) are packed tightly with little waste. The single long sentence holding all three format descriptions is dense but still readable.

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 correctly explains what comes back (two sizes plus a zip) and where to find download links, so an agent knows the full call-and-fetch cycle. The missing definition of the photo_tryon format is the remaining hole; everything else needed to call it correctly is present.

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?

The description does the heavy lifting the schema omits by explaining what three formats produce and what each costs, which is real added meaning. However, the schema enum contains four values and only three are covered: photo_tryon is listed in the enum but never explained or priced, leaving the agent guessing on a valid input. With 50% schema coverage and one enum value undocumented in both places, this lands at minimum-viable-plus.

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?

"Queue a set of AI photos for one catalog product" gives a specific verb (queue), resource (AI photo set), and scope (one catalog product), which cleanly separates it from create_image, generate_static_ads, make_angles and the other visual siblings. An agent can route to it without opening the schema.

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?

It supplies a prerequisite (photo_infographic "needs enough facts on the product page") and an explicit next step ("Poll list_photo_sets for download links"), which is the practical workflow guidance an agent needs. It stops short of naming when to prefer a sibling such as create_image or make_angles instead, so there is no explicit exclusion rule.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.