Skip to main content
Glama

Nova Amazon MCP Server

import_cogs

Destructive

Import COGS (cost of goods) rows for ONE seller account — TWO-STEP, never skip the preview: call WITHOUT commit first; the server validates and returns per-row warnings, a SKU-grain diff and a confirmationToken. SHOW the diff and warnings to the user and only after their explicit approval call again with the SAME account/mode/region/rows plus commit:true and the token. Mode 'merge' (default, safe for partial files) touches ONLY the keys you send: a 'fixed' row replaces the same period of its (asin, sku, region) and other periods survive; 'fifo' rows REPLACE that SKU's whole batch ladder — send the complete ladder (read it first with get_cogs_worksheet). Mode 'replace' wipes and restates every (account, region) present in rows — destructive with a partial payload, only for a full-region statement. Up to 2000 rows per call; for bigger files send several merge-mode calls. A Vendor Central (1P) account takes the vendor's own product cost, period-based only: 'fifo' rows are refused for it. Requires the OAuth connection (not a workspace API token) 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_cogs"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo'merge' (default): only the sent keys change. 'replace': wipe + 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.
regionNoDefault COGS region for rows that do not carry their own.
accountYesThe seller account (seller_partner_id, or an unambiguous account name) the rows belong to. 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. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare destructiveHint=true, and the description goes well beyond that by naming exactly what is destroyed under each mode: 'fixed' preserves other periods, 'fifo' replaces the whole batch ladder, 'replace' wipes every (account, region) in rows. It also discloses the preview/confirmationToken gate, the 2000-row cap, and the OAuth-plus-OWNER-role auth requirement — none of which the annotations 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?

The critical constraint ('TWO-STEP, never skip the preview') is front-loaded in the first clause, and each subsequent sentence covers a distinct hazard: mode semantics, row limits, 1P restriction, auth. It is dense and long, but almost no sentence is redundant; a slight trim of the auth/permission sentence would tighten it.

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?

No output schema exists, yet the description tells the agent what the preview returns (per-row warnings, SKU-grain diff, confirmationToken), which is exactly the missing return-value information. Combined with the mutation hazards, limits, and auth requirements, nothing an agent needs to call this safely is absent.

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 coverage is 86%, so the schema already carries most parameter meaning and the baseline is 3. The description adds genuine value on 'mode' semantics (what merge touches vs what replace wipes) and on the fifo/quantity coupling, but it does not clarify the call-level 'region' fallback, 'reason', or the cost-breakdown fields beyond what the schema states.

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 COGS rows') with an explicit scope constraint ('for ONE seller account'), which immediately separates it from read siblings like get_cogs_worksheet and from import_fbm_costs. An agent knows what it writes and to whom without opening the 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?

Gives explicit when-to-use rules for each mode ('merge' safe for partial files, 'replace' only for a full-region statement), tells the agent to read the ladder first via get_cogs_worksheet, and bans 'fifo' for 1P vendor accounts. It also names the mandatory two-step flow and the alternatives for large files (several merge calls).

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.