Catalog QA Desk

Draft a listing from a product photo

describe_product_photo

Read-only

Use this when the user has a photo of an item they want to sell or list (eBay, Shopify, Etsy, a marketplace post) and wants a listing draft from it. Pass the photo as file, image_url (a public https link) or image_base64. Returns the product type, the brand and model only when printed on the item (a brand guessed from the design comes apart as likely_brand, marked as a guess), colour, material, visible wear, items shown with it, a title under 80 characters, bullet points, and what to ask the seller. One JPEG, PNG, WebP or HEIC image up to 8 MB. It never invents a model number, a size or a condition grade. The photo goes once to a free Google Gemini model and nothing is kept. Not for photos of people, or for checking whether an item is genuine.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "describe_product_photo"
  }
}

Input Schema

Name	Required	Description
`file`	No	The product photo the user attached in the chat.
`image_url`	No	A public https link to one JPEG, PNG, WebP or HEIC photo, up to 8 MB, of the item alone: a photo with a person in it, such as clothing being worn, is refused, so ask for the item laid flat. Send exactly one of file, image_url and image_base64. Example call: {"image_url": "https://upload.wikimedia.org/wikipedia/commons/e/e6/Leica_M6_TTL_front.jpg"}
`image_base64`	No	The photo bytes as base64 (a data: URL is accepted), up to 8 MB.

Output Schema

Name	Required	Description
`brand`	Yes	Only when printed or clearly legible on the item.
`model`	Yes	Only when printed or clearly legible on the item.
`title`	Yes
`colour`	Yes
`notice`	Yes
`status`	Yes
`bullets`	Yes
`message`	Yes
`material`	Yes
`ask_seller`	Yes	What the photo cannot show, to ask the seller: serial number, whether it works, size, age.
`likely_brand`	Yes	A brand (and model line) guessed from the design because none is printed: a guess for the seller to confirm, never a fact for the listing.
`printed_text`	Yes	The text the model read on the item; brand and model are checked against it.
`product_type`	Yes
`visible_wear`	Yes
`included_items`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld), and the description adds genuinely new behavior: one image only, 8 MB cap, the photo is sent once to a free Gemini model with nothing retained, and the model will not invent a model number, size or condition grade, falling back to a flagged likely_brand guess. It stops short of describing how partial or unreadable photos are handled, so it is strong rather than complete.

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 trigger and image-source options, then the return payload, then limits and guardrails. It is dense but every sentence carries information; the only near-waste is repeating the format and 8 MB limit that the schema already states.

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?

Covers trigger, exclusions, input modes, fallback/guessing policy and privacy handling; an output schema exists, so the return-field rundown is optional surplus rather than a gap. Behavior on failed or ambiguous extractions is the one thing an agent might still wonder about.

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%, so the three input modes, HTTPS requirement, formats and size limit are already documented in the schema. The description restates the three-way choice and the one-image limit but adds little beyond that, so the baseline of 3 applies.

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 and resource ('draft a listing from a product photo') plus the concrete marketplaces it serves, and explicitly rules out adjacent jobs like authenticity checks. An agent can distinguish it from listing_text_audit or listing_fix_sheet without opening a 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?

Gives a trigger condition ('user has a photo of an item they want to sell or list') and explicit exclusions ('Not for photos of people, or for checking whether an item is genuine'), plus the practical workaround of asking for the item laid flat when clothing is worn. Nothing about when/where not to call 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.

All Catalog QA Desk tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.