Skip to main content
Glama

Nova Amazon MCP Server

query_inbound_shipments

Read-only

FBA INBOUND SHIPMENTS — the app's Inventory › Inbound shipments panel, the same service the page calls (POST /v2/shipments): every shipment of the last 18 months at its CURRENT state, one record per shipment with its SKU lines (quantity shipped and received per SKU). Answers: what is on its way to Amazon, what Amazon has received so far, which closed shipments came up short (the reconciliation list), which SKU or ASIN has units in transit. category is the panel's own split: planned (WORKING / READY_TO_SHIP — units still with the seller, NOT inbound yet), in_progress (SHIPPED / IN_TRANSIT / DELIVERED / CHECKED_IN / RECEIVING with units still to receive), closed_incomplete (CLOSED and received < shipped), closed_complete (CLOSED and received >= shipped — Amazon sometimes receives more than declared). With sku or asin the category is judged on THAT product's lines, not on the whole shipment. ⚠️ Three things Amazon does not give, so neither does this tool: NO DATES (the inbound API exposes no shipped-at / received-at; fetchedAt is when Nova last read the shipment, nightly at 01:30 UTC, never a business date — within a category rows come in lifecycle order, and by missing units for closed_incomplete); marketplaceId is the marketplace Nova asked Amazon for, not where the shipment lives (the API ignores it) — read stockLocation / fcCountry, derived from the destination FC code; NO SHIPMENT COST anywhere (the inbound fees are query_metrics' fee keys, per SKU and day). isFromAwd flags an AWD → FBA replenishment leaving Amazon's own warehouse, not the seller's. Not a metrics tool: no period, no aggregation — read the counts off the records, or ask query_inventory for totalFbaIncoming / inboundUnits per SKU. SUMMARY (summary=true, 2026-10-22): the counters behind the Inventory page's « N shipments » pill, per product × stock location (POST /v2/shipments/summary), for the skus and / or asins given (a SKU on its own lines, an ASIN over all its SKUs), in stockLocation or in every location: openCount (shipments on their way: they left the seller and units are still to receive), awdCount (of them, the AWD → FBA replenishments), plannedCount (WORKING / READY_TO_SHIP, nothing left yet), incompleteCount (CLOSED with fewer units received than shipped), inboundUnits (the product's units still expected on the open ones) and missingUnits (its units never received on the closed ones); a product × location with none of these has no entry. At most 400 product × location pairs a call. On the list, dateFrom / dateTo bound fetchedAt and sortBy / sortOrder rank the shipments by one of the panel's columns.

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": "query_inbound_shipments"
  }
}

Input Schema

NameRequiredDescriptionDefault
skuNoOnly shipments carrying this SKU; the category is judged on its lines.
asinNoOnly shipments carrying this ASIN; the category is judged on its lines.
skusNoWith summary=true: the SKUs to count, each on its own lines.
asinsNoWith summary=true: the ASINs to count, over all their SKUs.
limitNo
dateToNoKeep the shipments Nova last read (fetchedAt) on or before this day, the whole day (YYYY-MM-DD, UTC).
offsetNoRow offset for pagination (default 0).
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.
sortByNoRank the shipments by this column of the panel instead of each category's own order (lifecycle; missing units first for closed_incomplete).
summaryNotrue = the per product × stock location counters of the page's shipment pill (SUMMARY above) instead of the shipments: needs `skus` and / or `asins`; `stockLocation` keeps one location (a stock region such as 'EU_FBA' is read as its location), omit it for every location.
accountsNoRestrict to a subset of your own seller account IDs (from list_accounts). Omit to include all your accounts. A brand/account name is accepted and resolved to its id when it matches one of your accounts unambiguously; a label that carries the id ("Brand (A1B2C3D4E5F6G)") resolves to that id.
categoryNoThe panel's bucket: planned | in_progress (on the way) | closed_incomplete | closed_complete. Omit for every tracked shipment.
dateFromNoKeep the shipments Nova last read (fetchedAt) on or after this day (YYYY-MM-DD, UTC). fetchedAt is never a business date.
statusesNoAmazon statuses to keep (WORKING, READY_TO_SHIP, SHIPPED, IN_TRANSIT, DELIVERED, CHECKED_IN, RECEIVING, CLOSED). Prefer `category`.
sortOrderNoWith sortBy: desc (default) = highest first; asc = lowest first.
searchTextNoFree text over the shipment id, its name and the destination FC code.
shipmentIdNoOne FBA shipment id (FBA…).
stockLocationNoDestination stock pool, from the FC code: USA, Canada, Mexico, Brazil, UK, Pan-EU, India, Japan, Australia, UAE, Singapore, Egypt. With summary=true, omit it to count every location.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

With annotations already covering readOnlyHint, openWorldHint=false, and destructiveHint=false, the description adds substantial operational context: fetchedAt is a nightly read timestamp (01:30 UTC), never a business date; the inbound API exposes no shipped-at/received-at dates; marketplaceId is merely what Nova requested and not where the shipment lives; no shipment cost exists in this tool; isFromAwd signals an AWD→FBA replenishment; and closed_incomplete rows are ordered by missing units. This is rich behavioral disclosure beyond the annotations.

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 but front-loads the core identity and then organizes caveats and summary mode into distinct blocks. It is dense with useful distinctions rather than filler. Minor redundancy exists, such as repeating that fetchedAt is not a business date, and the warning block is heavy, but the structure remains navigable for an 18-parameter tool.

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 complex 18-parameter, zero-required-parameter tool with no output schema, the description covers the record shape ('one record per shipment with its SKU lines'), the summary-mode counters, the category definitions, the date and marketplace caveats, the cost omission, and the AWD flag meaning. It gives an agent enough context to call the tool correctly and interpret the main outputs without needing an output schema.

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 description coverage is already 94%, so the baseline is 3. The description still adds meaning beyond the schema for key parameters: it defines each `category` bucket (planned, in_progress, closed_incomplete, closed_complete), explains that `sku`/`asin` narrow category judgment to that product's lines, clarifies `summary=true` semantics and the `stockLocation` omission rule, explains `accounts` name/ID resolution, and states that `sortBy` overrides each category's default lifecycle order.

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 opens with a specific verb+resource and scope: 'FBA INBOUND SHIPMENTS — the app's Inventory › Inbound shipments panel... every shipment of the last 18 months at its CURRENT state, one record per shipment with its SKU lines.' It then explicitly distinguishes itself from a metrics tool and names query_inventory as the alternative for aggregated counts, so an agent can separate it from siblings without opening schemas.

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?

Usage is unusually explicit: it defines when to use list mode versus summary mode, when to pass `sku`/`asin` (category judged on that product's lines), when to prefer `category` over `statuses`, and when to ask query_inventory instead for totalFbaIncoming/inboundUnits. It also states the 400 product × location cap for summary calls and explains how dateFrom/dateTo and sortBy operate in list mode.

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.