Skip to main content
Glama

Settlement economics

get_settlement_economics
Read-only

Get settlement-report finalized financial data. This tool is backed by settlement reports and can lag recent Payments / Transaction View rows until Amazon finalizes the settlement period; use get_payment_transactions for recent refund, deferred, or payment transaction rows before settlement finalization. Summary mode (default): pivoted economics by ASIN when resolvable, otherwise by SKU, including source-signed order_item_price, refund_item_price, refund_net, principal quantity, and FBAPerUnitFulfillmentFee amount/quantity/per-unit value. revenue remains all ItemPrice rows for backward compatibility. The per-unit fulfillment fee is signed like the settlement fee amount. Summary fee fields commission (Amazon's referral fee, from amount_description Commission), item_fees (all item-level fees: commission, fulfillment, refund/shipping/giftwrap chargebacks), fba_fee, and fba_per_unit_fulfillment_fee overlap and are not additive; use net or total_fees for period totals. Summary mode also returns unattributed_fees: account-level settlement-report fees (AWD, removal orders, Deal/Vine/Premium Services, quarterly returns fees) that carry no SKU and cannot be attributed to an ASIN, grouped by fee type with a total (these are excluded from the per-ASIN pivot). This is a date-window ASIN analysis, not an exact Amazon disbursement statement: a window can contain multiple settlement IDs, and transaction families present in the live Payments feed might be absent from the V2 settlement report. For exact finalized disbursement-group reconciliation, use get_payment_transactions with financial_event_group_id and transaction_status=RELEASED, following pagination until complete. Detail mode: raw settlement-report rows filtered by amount type or amount description. settlement_effective_date uses posted_date, then posted_date_time, settlement_end_date, deposit_date, and finally snapshot_date because Amazon settlement rows can omit posted_date. marketplace_currency is inferred from the scoped Amazon marketplace when settlement item rows omit currency. asin_resolution explains how ASIN was attached to settlement rows: order_item_asin comes from the order item table and is preferred when available; historical_sku_asin comes from historical order-item SKU maps; active_listing_sku comes from active-listing SKU maps; settlement_text_asin parses an ASIN embedded in the fee text (for example FBA customer-returns fees). Rows that cannot be mapped to an ASIN are still returned at SKU grain instead of being suppressed. Currency note: settlement rows do not carry a reliable per-row currency, so marketplace_currency is asserted from the scoped marketplace and amounts are not currency-filtered; if the account transacts in multiple currencies (e.g. a North America unified account) settlement amounts may combine currencies, so use get_financial_events (scoped to the marketplace currency by default) to isolate a single currency.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
skuNoFilter by SKU
asinNoFilter by ASIN
limitNoMax rows (1-1000, default 20).
detailNotrue = raw settlement rows, false = pivoted per-ASIN summary
offsetNoPagination offset (0-100000, default 0). Use the returned pagination.next_offset to continue.
sort_byNoColumn to sort by (summary mode)revenue
end_dateNoOptional. YYYY-MM-DD end date for settlement_effective_date.
sort_orderNoSort orderdesc
start_dateNoOptional. YYYY-MM-DD start date for settlement_effective_date.
amount_typeNoDetail mode only. Filter by amount type (e.g. ItemPrice, ItemFees, Promotion).
include_raw_rowsNoFalse returns compact rows. Default true.
amount_descriptionNoDetail mode only. Filter by amount description (e.g. FBAPerUnitFulfillmentFee).
include_diagnosticsNoTrue may add expanded freshness diagnostics. Basic empty-result data-window diagnostics are included by default when available.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
evidenceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnlyHint=true, destructiveHint=false), and the description goes well beyond them: settlement lag versus live Payments rows, non-additive/overlapping fee fields (commission, item_fees, fba_fee), unattributable account-level fees, the ASIN resolution fallback chain, and the multi-currency caveat. This is exactly the kind of behavior an agent needs and that annotations alone cannot 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 purpose and routing guidance are front-loaded in the first two sentences, and most of the remaining length is substantively necessary given 13 parameters, two output modes, and currency caveats. However, the text is a dense unbroken block with no headings or bullets, making it harder to scan than it needs to be.

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 an output schema present, the description needn't explain return values, and it covers everything else: which mode returns what, edge cases (unattributed fees, unmapped ASINs at SKU grain), data-freshness limitations, and the routing to sibling tools. Nothing an agent needs to call this correctly is 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, but the description adds real meaning beyond the schema: the summary-vs-detail mode distinction, that amount_type/amount_description apply only in detail mode, the settlement_effective_date fallback chain, and how marketplace_currency is inferred. It does not explain every parameter (e.g., sort_by, include_raw_rows), so it falls short of 5.

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 opening line states a specific verb and resource ('Get settlement-report finalized financial data') and immediately differentiates itself from siblings by naming get_payment_transactions and get_financial_events with the conditions that select each. An agent can distinguish this tool from its closest alternatives without opening any 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?

It gives explicit when-to-use guidance: use get_payment_transactions for recent refund/deferred/payment rows before settlement finalization, use it with financial_event_group_id and transaction_status=RELEASED for exact disbursement reconciliation, and use get_financial_events to isolate a single currency. These are concrete alternatives with the conditions that trigger them, not vague hints.

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.