Skip to main content
Glama

Nova Amazon MCP Server

update_listing_content

Destructive

Seller Central only (a Vendor Central account is refused by name: its content is changed in Vendor Central). Change listing CONTENT on Amazon (title, bullets, description, backend keywords, dimensions, any editable product-type attribute — never the offer: price, stock, shipping, tax, condition or offer images, which Nova refuses as not-editable) for up to 50 SKUs of ONE account on ONE marketplace. Each row is { sku, attributes: { column: value } } with the columns get_listing_content returns: a string for a text attribute, an array of strings for bullet_point, a number for a numeric leaf, null to DELETE an attribute; a column you omit is untouched. TWO-STEP, never skip the preview: call WITHOUT commit; the server diffs against Amazon's current values, validates locally against the product type schema and on Amazon (VALIDATION_PREVIEW — nothing is written), and returns the before → after table, the issues and a confirmationToken; show them to the user and only after explicit approval call again with the SAME account/marketplace/rows plus commit:true and the token. ACCEPTED means Amazon took the change for processing; STORED (about two minutes later) means Amazon holds it; PUBLISHED means the public product page shows it, verified on the public catalogue within minutes to hours and re-checked for 72 hours. get_listing_change_status gives each status with its clocks and the next check. For more than 50 SKUs, point the user to the bulk template in Nova. Requires the OAuth connection, the OWNER role, and the Amazon write flag on the workspace.

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": {
      "account": "<account>",
      "marketplace": "<marketplace>",
      "rows": "<rows>"
    },
    "name": "update_listing_content"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYes
commitNoOmit/false = preview (diff + validation on Amazon, no write). true = write; requires the confirmationToken from the preview.
reasonNoOne sentence, ALWAYS IN ENGLISH (regardless of the conversation language), on WHY you are making this call — the user question or your analytical goal. Recorded so the seller can see how their data is used.
accountYesThe seller account (seller_partner_id, or an unambiguous account name). One account per call.
marketplaceYesA country code (FR), a domain (amazon.fr) or the Amazon marketplace id. One marketplace per call: an Amazon submission is per SKU × marketplace.
expectedBeforeNoReturned by the preview (sku → attribute → hash of the value shown as before). Resend it on commit: the write is refused if Amazon's value moved since the preview.
confirmationTokenNoThe token the preview returned — proves the user saw exactly this payload.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description goes well beyond them: it explains that a null value DELETES an attribute, that an omitted column is untouched, that the preview writes nothing (VALIDATION_PREVIEW), that the confirmationToken proves the user saw the payload, that expectedBefore refuses the write if Amazon's value moved, and that the call requires OAuth, the OWNER role and the workspace write flag. The only thing left implicit is the shape of the returned issue list.

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 most decision-relevant constraint (Seller Central only) and dense with usable information, but it is a single very long paragraph with parenthetical asides that could be broken into a short scannable structure. Little is wasted, yet the wall-of-text form makes the two-step rule and the status vocabulary harder to extract than necessary.

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 a destructive, open-world write tool with nested parameters and no output schema, the description covers everything an agent needs: preconditions, field scope, encoding rules, the preview/commit protocol, the preview's return content, and the ACCEPTED/STORED/PUBLISHED status semantics with their time horizons. Nothing material is left to inference.

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 86%, so the baseline is 3; the description earns an extra point by specifying the row shape { sku, attributes: { column: value } } and the per-type encoding rules (string for text, array of strings for bullet_point, number for a numeric leaf, null to delete, omit to leave untouched), which the schema's free-form additionalProperties does not convey. It also reinforces the commit/token pairing and the requirement to resend the SAME account/marketplace/rows on commit.

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 (change listing CONTENT on Amazon) and enumerates the covered fields (title, bullets, description, backend keywords, dimensions, product-type attributes) while explicitly excluding the offer fields. It also carves out the sibling read path (columns get_listing_content returns) and the status path, so an agent can distinguish it from get_listing_content and get_listing_change_status without opening either 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?

Explicit when-to-use and when-not: Seller Central only, Vendor Central is refused by name, and more than 50 SKUs routes the user to the bulk template. It also prescribes the mandatory two-step flow (preview without commit, then commit only after explicit user approval with the token) and names get_listing_change_status for follow-up.

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.