Resollo Agent API

Create a Resollo product listing from photos

products.create

Creates a new Resollo product listing FROM PHOTOS ONLY -- Resollo's own built-in AI (the same pipeline the web listing form's 'AI autofill' button uses) analyzes the images and generates the title, description, category, condition, and a suggested price; this tool never accepts or generates listing content on its own. The listing is created INACTIVE and NOT publicly visible -- it does NOT go live automatically. The seller MUST review and activate it themselves on their existing Resollo product management page (the activation_url returned by this tool) before it becomes visible or goes through moderation. Never tell the user the listing is 'live' or 'published' after calling this tool -- tell them a draft was created from their photos and they need to review and activate it themselves at resollo.com. Images must be actual photo files the caller has access to (e.g. local files) -- never fetch or invent an image from a URL. Requires an 'Authorization: Bearer ' header -- generate a key from the Resollo profile page; the resulting listing is attributed to that key's user.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	No	Optional override for the AI-generated title.
`unit`	No	Unit of sale (default "piece").	piece
`price`	No	Optional fixed price override. When omitted, Resollo's AI price-suggestion sets it.
`images`	Yes	1-5 real photo files of the item. Resollo's own AI generates the listing content from these.
`quantity`	No	Units available (default 1).
`condition`	No	Optional override for the AI-chosen condition code (see getMarketplaceInfo.conditions).
`guarantee`	No	Optional warranty / guarantee text.
`category_id`	No	Optional override for the AI-chosen category id (see getMarketplaceInfo.categories).
`description`	No	Optional override for the AI-generated description.
`offers_enabled`	No	Whether buyers may send Make-an-Offer bids on the listing.
`is_business_listing`	No	Whether this is a business (vs. private) listing.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`state`	Yes
`suggested`	Yes
`product_id`	Yes
`activation_url`	Yes
`quota_remaining`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

AddedAug 27, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations are neutral (readOnlyHint=false, openWorldHint=false, destructiveHint=false), so the description carries the burden and delivers richly: listing is created INACTIVE and not publicly visible, the seller must manually review/activate via activation_url, content is AI-generated server-side, the listing is attributed to the API key's user, and post-call agent messaging is prescribed (never say 'live' or 'published'). This far exceeds what the annotations convey.

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 description is long (~230 words) but every sentence earns its place for a side-effecting tool: activation flow, auth requirement, image constraints, and post-call user messaging are all load-bearing. There is some redundancy (the photos-only concept is stated three times), and the 'web listing form AI autofill' comparison is nice-to-have rather than essential, so it is not a zero-waste 5.

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 11-parameter, side-effecting creation tool with an output schema, the description is complete: it covers post-conditions (inactive draft), the manual activation step, the activation_url return value, auth key sourcing and attribution, image sourcing constraints, and the exact messaging the agent must give the user. Nothing an agent needs to call this correctly and handle the aftermath 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 coverage is 100%, so every parameter already has a meaningful description, including that images must be base64 bytes and never URLs, and that name/price/condition/category_id/description are AI overrides. The description reinforces the photos-only constraint and tie to the 'AI autofill' pipeline, but adds little parameter-specific meaning beyond the schema. Baseline 3 is appropriate.

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 leads with a specific verb, resource, and the defining mechanism: 'Creates a new Resollo product listing FROM PHOTOS ONLY'. It precisely distinguishes itself from the read/search siblings (products.get, products.search) by anchoring on photo-driven AI generation, and the title reinforces the same scope.

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?

The description gives clear when-to-use context (you have photo files of an item) and explicit exclusions: never accept direct listing content, never fetch or invent an image from a URL. However, it never names a sibling alternative or explicitly states when to choose another tool (e.g., products.search for retrieval), so it stops short of a 5.

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

All Resollo Agent API tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation5/5

Each tool is cleanly grouped by resource (marketplace, offers, orders, products, questions, reviews, sellers) and within a group every action is distinct. There is no real overlap between e.g. orders.place, orders.checkoutLink, and orders.status, or between offers.make and offers.respond.

Naming Consistency4/5

Tool names follow a predictable resource.action pattern with lowercase verb-like second segments (offers.list, products.create, questions.ask). Minor deviations exist: orders.checkoutLink uses camelCase and sellers.listings is a noun rather than a verb, but the overall convention remains easy to infer.

Tool Count3/5

18 tools sits in the 16-25 borderline-heavy range. The marketplace scope is broad enough that most tools feel justified, but the count is slightly above the ideal well-scoped band and could be seen as heavy for a single API server.

Completeness3/5

The server covers core marketplace browsing, product draft creation, order placement, offers, questions, and reviews well. However, there are notable lifecycle gaps: products can be created but not updated/deleted/activated via API, orders have no dispatch/confirm/receive actions, and offers have no cancel action, with several operations pushed to the web UI.

Resources

Need Help?