Skip to main content
Glama

Nova Amazon MCP Server

get_cogs_worksheet

Read-only

One region's COGS worksheet — the import template as JSON: a row per (account, ASIN, SKU) product of the catalogue (products narrows the list like the Products filter of the COGS page) and per existing cost period/batch, with the CURRENT value (currentCogs null = no COGS yet). Use it to match a seller's source file to exact SKUs/ASINs before building import_cogs rows (match by SKU first, ASIN as fallback), and to read a SKU's full FIFO ladder before restating it. missingOnly=true keeps only rows without a value. Paginate with limit/offset (total is returned). Vendor Central (1P) products are listed too, each row then carrying its channel ('SELLER' = Seller Central, 'VENDOR' = Vendor Central).

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": {
      "region": "<region>"
    },
    "name": "get_cogs_worksheet"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
offsetNo
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.
regionYesCOGS region code (from get_setup domain=cogs): 'US', 'UK', the Pan-EU pool 'EU', an EU country ('DE', 'FR', …), …
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.
productsNoWhich products to list, like the Products filter of the COGS page: 'all' (default) = every listing, the dormant ones included; 'active' = the products Amazon holds Active, the ones not sold yet included; 'sold' = the products with a sale in the last 24 months, what the COGS page lists by default. Keep 'all' before an import_cogs in mode 'replace': a replace removes every cost of the region the rows do not restate, the costs of the products a narrower list leaves out included.
missingOnlyNotrue = only products without a current COGS value.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / products
      Added value: +{
      +  "description": "Which products to list, like the Products filter of the COGS page: 'all' (default) = every listing, the dormant ones included; 'active' = the products Amazon holds Active, the ones not sold yet included; 'sold' = the products with a sale in the last 24 months, what the COGS page lists by default. Keep 'all' before an import_cogs in mode 'replace': a replace removes every cost of the region the rows do not restate, the costs of the products a narrower list leaves out included.",
      +  "enum": [
      +    "sold",
      +    "active",
      +    "all"
      +  ],
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / region / description
      Previous value: -"COGS region code (from get_cogs_setup): 'US', 'UK', the Pan-EU pool 'EU', an EU country ('DE', 'FR', …), …"New value: +"COGS region code (from get_setup domain=cogs): 'US', 'UK', the Pan-EU pool 'EU', an EU country ('DE', 'FR', …), …"
  3. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly=true and destructive=false, yet the description adds real behavioral context: currentCogs null means no COGS yet, missingOnly filters rows without a value, pagination via limit/offset with total returned, and a channel field distinguishing Seller Central from Vendor Central (1P) rows. It does not mention error behavior or rate limits, but the disclosure beyond the annotations is substantial.

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?

It is front-loaded with the core definition and the practical instruction before the peripheral details, and every sentence carries information. The single dense paragraph with nested parentheticals is somewhat crammed, making the pagination and vendor-channel notes easy to skim past.

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?

With no output schema, the description takes on the burden of explaining the return shape and does so: row grain, the currentCogs field and its null meaning, the channel field, and the pagination total. Combined with the import_cogs workflow guidance, an agent has enough to call it and interpret the results correctly.

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 71%, and the description adds meaning the schema alone would not convey: the products enum is tied to the COGS page filter and to replace-mode safety, missingOnly to missing-value rows, and limit/offset to pagination with a returned total. region and accounts are left to their schema descriptions, so it does not fully close the remaining gap.

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 names a specific resource and return shape: a regional COGS worksheet serialized as JSON, with a row per (account, ASIN, SKU) and per cost period/batch, carrying the current value. It tells the agent exactly what the payload represents (the import template), which distinguishes it from worksheet siblings like get_stock_worksheet or get_fbm_worksheet.

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?

It gives explicit when-to-use directions: match a seller source file to exact SKUs/ASINs before building import_cogs rows, matching by SKU first and ASIN as fallback, and read a SKU's full FIFO ladder before restating it. It also warns to keep products='all' before an import_cogs replace, because a replace removes costs for rows not restated — a genuine when-not condition.

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.