vivid-ads-commerce

Place an order (creates a draft for team review)

vivid_place_order

Create a Shopify DRAFT order for Vivid Ads team review — NOT a final/placed order, and NEVER charges a card. Before calling, summarise the exact product, quantity, configuration, verified price (if available), customer details, and delivery/pickup, then get the customer's explicit confirmation. Call WITHOUT confirm to get a Review summary; confirm:true only AFTER they confirm. Do NOT auto-retry after a timeout without first checking whether a draft was already created. Payment is a secure invoice/pay-link from the team; production waits on proof approval. Artwork is OPTIONAL here: an order can be placed with no file at all — the customer uploads later via the upload link emailed when the order is placed, or any time from My Account on the customer portal (portal.vividads.com.au), so never hold up an order waiting for artwork.

Input Schema

Name	Required	Description
`name`	No
`size`	No
`email`	Yes
`items`	No	For a MULTI-LINE order (e.g. two banners with DIFFERENT designs): one entry per line, each { product, size?, options?, quantity?, artwork? }. Different designs must be SEPARATE entries (quantity 1 each) with their OWN artwork. If provided, this replaces the single top-level product; contact/delivery/PO stay at the top level.
`phone`	No
`artwork`	No	{ mode:'ai_design'\|'upload_file'\|'design_brief', designId?, imageUrl?, printPdfUrl?, fileUrl?, brief? }
`company`	No
`confirm`	No	set true ONLY after the customer reviews and confirms
`options`	No	FULL selected options (same shape as vivid_price.options). Use vivid_product to see them. Prefer this over `size` for option-rich products.
`product`	No
`delivery`	No	pickup or delivery details. PICKUP: { method:'pickup', name, email, phone, pickupLocation?, notes? }. DELIVERY: { method:'delivery', name, email, phone, company?, address1, address2?, suburb, state, postcode, country, notes? }. Contact (name/email/phone) can live here or at the top level. Omit entirely to keep the old behaviour.
`poNumber`	No
`quantity`	No
`customerType`	No	retail\|corporate\|school\|government\|account — sets payment terms
`idempotency_key`	No	optional: a unique key for this request — a retry with the same key returns the first result instead of repeating the action

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 20, 2026

addedInput schema / properties / idempotency_key

Added value: +{
+  "description": "optional: a unique key for this request — a retry with the same key returns the first result instead of repeating the action",
+  "maxLength": 128,
+  "type": "string"
+}

First observedJul 19, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) only give the safety envelope; the description adds real substance — draft-not-final semantics, no card charge, invoice/pay-link payment, and production gated on proof approval. The one gap is that retry/idempotency behaviour is left to the schema's idempotency_key description rather than being reconciled with idempotentHint=false here.

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 single most important distinction (draft vs placed order) and each sentence carries a distinct instruction or warning. It is dense and parenthetical-heavy, but almost nothing is redundant; a small trim of the portal URL aside would tighten it further.

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?

For a 15-param, nested, no-output-schema mutation tool, it covers the critical workflow: confirm gating, artwork optionality, payment path, and retry caution. The main missing piece is what the two call modes actually return (review summary vs. created draft), which an agent would benefit from knowing given no output schema exists.

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 only 47% across 15 params, but the description compensates by mapping the pre-call checklist (product, quantity, configuration, price, customer details, delivery/pickup) onto the fields and by clarifying that confirm gates the write and artwork is optional. It adds meaning beyond the raw schema for the highest-risk params, though a few (name, phone, poNumber, quantity) remain undocumented in both places.

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 ('Create a Shopify DRAFT order for Vivid Ads team review') and immediately scopes it against the obvious misread ('NOT a final/placed order, and NEVER charges a card'). This cleanly distinguishes it from siblings like vivid_reorder, vivid_accept_quote, and vivid_request_quote.

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?

Explicit call protocol: call without confirm for a Review summary, set confirm:true only after customer confirmation, and do not auto-retry after a timeout without checking whether a draft already exists. It also pre-empts a common failure mode by stating artwork is optional and must not block the order.

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

All vivid-ads-commerce 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.

Resources

Need Help?