Skip to main content
Glama

Nova Amazon MCP Server

import_external_stock

Destructive

DEPRECATED (2026-10-22): use import_supply_chain (warehouseUnits and countedOn per line); this tool stays for callers that still use it. Import the EXTERNAL STOCK of ONE account — the units the seller holds OUTSIDE Amazon (own warehouse or 3PL), per product × stock region: the fourth rung of the coverage ladder, what query_inventory returns as externalStock and counts in coverageWithExternal / recommendedOrderQty. A count is CURRENT state, not a movement: one row per (product, region) with the units on hand and the count date; 0 is a real count, an absent row means unknown (never 0). TWO-STEP like import_stock_params: preview WITHOUT commit (warnings + per-region diff + confirmationToken), show the user, then commit with the token. Mode 'merge' (default) upserts only the (ASIN, region) rows you send; 'replace' restates every (account, region) present in rows — a product absent from rows loses its count there. Up to 2000 rows per call. Requires the OAuth connection and the OWNER role.

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>",
      "rows": "<rows>"
    },
    "name": "import_external_stock"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo'merge' (default): only the sent rows change. 'replace': restate each (account, region) present in rows.
rowsYes
commitNoOmit/false = preview (validate + diff, 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.
confirmationTokenNoThe token the preview returned — proves the user saw exactly this payload.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / rows / items / properties / region / description
      Previous value: -"A stock region as get_stock_setup lists them ('USA', 'EU_FBA', 'UK', 'Canada'…; 'US', 'EU', 'GB' are accepted). Never 'ALL': the units sit in one place."New value: +"A stock region as get_setup domain=stock lists them ('USA', 'EU_FBA', 'UK', 'Canada'…; 'US', 'EU', 'GB' are accepted). Never 'ALL': the units sit in one place."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: it spells out the destructive consequence behind destructiveHint=true ('a product absent from rows loses its count there' in replace mode), the 2000-row cap, the OWNER role and OAuth connection requirement, and the preview/confirmationToken gate. It also clarifies semantic traps the annotations can't express — 0 is a real count while an absent row means unknown.

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 deprecation notice is correctly front-loaded, then purpose, then workflow, then mode semantics — a sensible order for a long description. A few sentences duplicate schema text (the 2000-row cap, the token requirement), which is the only reason it falls short of 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 a destructive, two-step bulk import with no output schema, the definition covers everything an agent needs: replacement path, account scoping, row limits, permission requirements, commit gating, and the exact meaning of a zero vs missing row. Nothing material is left to guesswork.

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 description coverage is 83% and the nested row fields (asOf, region, quantity, location) are already documented in detail, so the baseline is 3. The description mostly restates that content (2000-row limit, merge/replace, 0-vs-absent) with only mild added framing about what replace does to omitted products; it adds little syntax or format meaning the schema does not already carry.

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 ('Import the EXTERNAL STOCK of ONE account') with scope (per product × stock region) and explicitly distinguishes itself from the sibling that supersedes it (import_supply_chain) and the analogous tool it mirrors (import_stock_params). The 'fourth rung of the coverage ladder' framing plus the link to query_inventory's externalStock / coverageWithExternal tells an agent exactly where this data lands.

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?

Gives explicit when-not guidance ('DEPRECATED... use import_supply_chain; this tool stays for callers that still use it'), a full two-step workflow (preview without commit, show user, then commit with token), and mode selection guidance (merge default vs replace). An agent knows both the alternative and the operating procedure without inferring anything.

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.