vivid-ads-commerce

Upload artwork

vivid_upload_artwork

Upload a customer's artwork FILE through the agent (no website file picker needed). Accepts the file as base64, stores it in Vivid's Google Drive, and returns a stable shareable link plus metadata. Accepts PDF / AI / EPS / JPG / PNG. Does NOT verify print-readiness — the team checks that. Uploading needs no verification, but ATTACHING the file to an existing order does: pass the identity token from vivid_identity_verify, otherwise the file is held unattached and the reply says so. Use when a customer wants to send their print file via chat.

Input Schema

Name	Required	Description
`email`	No	customer email (optional). Only recorded once verified — see token.
`token`	No	identity token from vivid_identity_verify. Required to attach this upload to an order or to record the email; without it the file is still stored, just not claimed by anyone.
`orderId`	No	attach to an existing order (optional). Ignored unless a valid token is supplied — an unverified caller must not be able to put a file on somebody else's order.
`quoteId`	No	associate with a quote request (optional)
`filename`	Yes	original filename incl. extension, e.g. 'banner-artwork.pdf'
`mimeType`	No	MIME type, e.g. 'application/pdf'
`sessionId`	No	associate with a design session (optional)
`contentBase64`	Yes	the file contents, base64-encoded (data URI prefix OK). Small files only; for very large files share a download link instead.
`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"
+}

Changed3 schema fields changedAug 4, 2026

changedInput schema / properties / email / description

Previous value: -"customer email to associate with the upload (optional but recommended)"New value: +"customer email (optional). Only recorded once verified — see token."

changedInput schema / properties / orderId / description

Previous value: -"associate with an order/draft (optional)"New value: +"attach to an existing order (optional). Ignored unless a valid token is supplied — an unverified caller must not be able to put a file on somebody else's order."

addedInput schema / properties / token

Added value: +{
+  "description": "identity token from vivid_identity_verify. Required to attach this upload to an order or to record the email; without it the file is still stored, just not claimed by anyone.",
+  "type": "string"
+}

First observedJul 19, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare readOnly=false, destructive=false, idempotent=false, openWorld=true; the description adds substantial context beyond them: it does NOT verify print-readiness, uploading needs no verification but attaching does, and an unverified upload is 'held unattached' with the reply saying so. That consequence-level disclosure is exactly what structured fields cannot 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?

Front-loads what the tool does and returns before the caveats, and every sentence carries information (formats, verification stance, token gate). Capitalized emphasis is slightly noisy and the paragraph is dense, but there is no filler.

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?

Even without an output schema, the description states the return shape (stable link plus metadata) and the security-gated attachment behavior. Format acceptance, storage destination, and the verification caveat are all covered, leaving nothing essential for correct invocation.

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 the baseline is 3, but the description reinforces the semantics that matter: the token gates attaching to an order and recording the email, and unauthenticated uploads are stored unclaimed. This ties token/orderId to a behavioral outcome the schema only implies.

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 ('Upload a customer's artwork FILE through the agent'), names the return value ('stable shareable link plus metadata'), and enumerates accepted formats. This clearly separates it from siblings like vivid_check_artwork or vivid_order_artwork by emphasizing raw file ingestion rather than verification or order attachment.

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?

Gives an explicit trigger ('Use when a customer wants to send their print file via chat') and clarifies the attach-vs-hold condition, naming vivid_identity_verify as the prerequisite for attaching. It stops short of routing the agent to alternatives for print-readiness (vivid_check_artwork) beyond noting the team checks that.

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?