Skip to main content
Glama

Nova Amazon MCP Server

query_pnl_bridge

Read-only

P&L BRIDGE: the order-based and the cash-based P&L of the same months side by side, and what separates them — for a finance team tying the commercial month (the orders) to the settlement month (the cash). view="month" (default): one row per calendar month over the accounts (and marketplaces) in scope with, for each P&L line (product sales, other sales, sales deductions, VAT, net sales, cost of goods, Amazon fees, FBM cost, PPC spend, DSP cost, net profit), the order reading (order), the cash reading (cash) and bridge = cash − order; sales splits the month's sales by TIMING on both sides (order sales whose principal was posted the same month / later / earlier / not yet; cash sales from lines purchased the same month / earlier months / later months / lines the order report does not know, of which sold to Amazon and without items) and gives the FX gap and the valuation gap of the same lines; fees does the same for the purchase-date fees (estimated at the order vs actually released). view="settlement": one row per settlement whose RELEASED postings fall in the months asked, most recent first, with the purchase months it pays (byPurchaseMonth, by marketplace and origin) and its own currency; settlementId narrows to one settlement and implies this view, and adds netProfitToDeposit: that settlement walked from the net profit of its cash P&L down to its deposit (the cost of goods Amazon never charged, the taxes that moved with the money, the reserves and other movements of the balance, what is left unallocated), in the settlement's own currency. Seller Central accounts only. 📐 HOW TO READ: amounts are as the marts store them — sales positive, costs and fees NEGATIVE (net profit = the sum of the lines); a positive bridge on a cost line means the cash reading spent less. Order basis = the day the order was purchased (what query_metrics serves by default); cash basis = the day Amazon POSTED the money, RELEASED postings only (what query_metrics serves with basis="cash"); a settlement = the RELEASED postings grouped under one settlement_id, the payout itself (the Transfer) excluded, so the sum of a settlement ties to the settlement report to the cent. Neither side has a live overlay: the current month is incomplete on both. Monetary values are in the organization's PRIMARY currency (currency in the response, the currency the marts are built in), never the caller's display preference; cashSalesLocal is in the settlement's own currency. total null = the bridge is not built in this environment; a null figure = not carried by the deployed bridge (unknown, never zero). Months are YYYY-MM.

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": {
      "from": "<from>",
      "to": "<to>"
    },
    "name": "query_pnl_bridge"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesLast month, INCLUSIVE (YYYY-MM). With view="settlement": the settlements whose released postings fall, at least in part, in from..to.
fromYesFirst month, INCLUSIVE (YYYY-MM).
viewNo"month" (default): by calendar month, the two P&L and the bridge. "settlement": by settlement, most recent first, the purchase months each one pays.
limitNoview="settlement": settlements served, 1 to 200 (default 50); `truncated` in the answer says when more fall in the window.
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.
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.
marketplacesNoMarketplaces to add up: country codes (US, DE), domains (amazon.de) or marketplace ids, as list_accounts gives them for each account. Omit for every marketplace of the accounts.
settlementIdNoONE settlement, by its settlement_id (the id of the settlement report) — implies view="settlement".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Despite readOnly/non-destructive annotations, the description discloses substantial behavior an annotation cannot convey: sign convention (costs and fees negative, positive bridge on a cost line means cash spent less), released-postings-only basis with the Transfer excluded, no live overlay so the current month is incomplete on both sides, settlement sums tying to the report to the cent, and null semantics ('total' null = bridge not deployed; null figure = unknown, never zero). It also pins currency behavior to the organization's primary currency rather than display preference, with cashSalesLocal the exception.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and the two views are clearly separated, but the text is a single dense block with long nested parentheticals enumerating every output column — much of it return-value documentation that would read better as an output schema or structured list. It is information-dense but heavy to parse.

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 carries the return shape itself, and it does so exhaustively for both views (per-line order/cash/bridge values, the sales timing split, fees, settlement byPurchaseMonth and netProfitToDeposit), plus the currency, sign and null caveats needed to interpret them. Nothing an agent needs to call or interpret this tool appears missing.

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 100%, so the baseline is 3; the description nevertheless adds meaning beyond the schema by specifying that settlementId implies view="settlement" and enriches that mode with netProfitToDeposit, and by clarifying the month basis for each view. It adds relatively little about the other parameters (from/to/limit) that the schema does not already state.

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?

Opens with a specific verb+resource definition — 'the order-based and the cash-based P&L of the same months side by side, and what separates them' — and explicitly positions it against the sibling query_metrics (order basis by default, basis="cash" for cash), so an agent can distinguish the two without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States the audience/use case (finance team tying the commercial month to the settlement month) and gives an explicit rule for choosing between the two modes: view="month" for monthly bridge rows, view="settlement" when settlement-level detail is needed, with settlementId implying that view. It does not explicitly say when to prefer this over query_metrics, only that query_metrics is the source of the underlying bases, so it stops short of a full when/when-not statement.

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.