Agent Central

Reimbursements

get_reimbursements

Read-only

Get FBA reimbursement records by date, ASIN or reason. Reasons use Amazon's report labels; known Finances descriptions are translated, while others are shown as received. When seller-scoped storage is enabled, the current view requires a proved selected seller and region. Unattributed legacy records remain separate and paginated, never additive seller history. seller_id and sp_api_region identify known ownership; marketplace_id is an import stamp, not native marketplace attribution. Product-label enrichment requires the same seller evidence; legacy source labels are not replaced with another seller's listing labels.

Input Schema

Name	Required	Description	Default
`asin`	No	Filter by ASIN
`limit`	No	Maximum number of rows to return (1-1000, default 20)
`offset`	No	Pagination offset (0-100000, default 0). Use the returned pagination.next_offset to continue.
`reason`	No	Filter by reimbursement reason, exact match on Amazon's report label (e.g. Lost_Warehouse, Lost_Inbound, CustomerReturn, Reimbursement_Reversal). Known Finances API spellings such as WAREHOUSE_LOST are accepted and translated.
`sort_by`	No	Column to sort results by	amount_total
`end_date`	No	Optional. YYYY-MM-DD end date for approval_date. The range may span at most 366 days.
`sort_order`	No	Sort direction	desc
`start_date`	No	Optional. YYYY-MM-DD start date for approval_date. The range may span at most 366 days.
`record_scope`	No	Select the current source view or the separately identified legacy records. Legacy ownership is unproven; views are never added together.	current
`include_raw_rows`	No	For tabular results, false returns compact rows capped at MCP_TEXT_ROW_PREVIEW_LIMIT (default 10), regardless of limit. Complete-page and custom non-tabular responses may ignore this option; see tool-specific notes. Default true; large full-row responses are capped separately. Freshness fields require include_diagnostics=true in either row mode, where supported.
`include_diagnostics`	No	True enables expanded freshness diagnostics. Where supported, snapshot_capture_at and snapshot_data_through_date are populated only when include_diagnostics=true, in both compact and full-row modes; values may still be null if source data is unavailable. Default false. Basic empty-result data-window diagnostics are included by default when available.

Output Schema

Name	Required	Description	Default
`evidence`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026

addedInput schema / properties / record_scope

Added value: +{
+  "default": "current",
+  "description": "Select the current source view or the separately identified legacy records. Legacy ownership is unproven; views are never added together.",
+  "enum": [
+    "current",
+    "unattributed_legacy"
+  ],
+  "type": "string"
+}

Changed29 schema fields changedNov 7, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / additionalProperties
```
Previous value: -trueNew value: +{}
```
removedOutput schema / properties / evidence / properties / effective_scope / $ref
```
Removed value: -"#/properties/evidence/properties/requested_scope"
```
addedOutput schema / properties / evidence / properties / effective_scope / additionalProperties
```
Added value: +false
```

addedOutput schema / properties / evidence / properties / effective_scope / properties

Added value: +{
+  "end_date": {
+    "anyOf": [
+      {
+        "format": "date",
+        "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "filters": {
+    "additionalProperties": {},
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  "group_by": {
+    "items": {
+      "maxLength": 128,
+      "minLength": 1,
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "marketplace_id": {
+    "anyOf": [
+      {
+        "minLength": 1,
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "reporting_time_zone": {
+    "anyOf": [
+      {
+        "minLength": 1,
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "sort": {
+    "items": {
+      "additionalProperties": false,
+      "properties": {
+        "direction": {
+          "enum": [
+            "asc",
+            "desc"
+          ],
+          "type": "string"
+        },
+        "field": {
+          "maxLength": 128,
+          "minLength": 1,
+          "type": "string"
+        }
+      },
+      "required": [
+        "field",
+        "direction"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "start_date": {
+    "anyOf": [
+      {
+        "format": "date",
+        "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  }
+}

addedOutput schema / properties / evidence / properties / effective_scope / required

Added value: +[
+  "marketplace_id",
+  "start_date",
+  "end_date",
+  "reporting_time_zone",
+  "group_by",
+  "sort",
+  "filters"
+]

addedOutput schema / properties / evidence / properties / effective_scope / type
```
Added value: +"object"
```
removedOutput schema / properties / evidence / properties / grain / items / $ref
```
Removed value: -"#/properties/evidence/properties/tool"
```
addedOutput schema / properties / evidence / properties / grain / items / maxLength
```
Added value: +128
```
addedOutput schema / properties / evidence / properties / grain / items / minLength
```
Added value: +1
```
addedOutput schema / properties / evidence / properties / grain / items / type
```
Added value: +"string"
```
removedOutput schema / properties / evidence / properties / join_keys / items / properties / field / $ref
```
Removed value: -"#/properties/evidence/properties/tool"
```
addedOutput schema / properties / evidence / properties / join_keys / items / properties / field / maxLength
```
Added value: +128
```
addedOutput schema / properties / evidence / properties / join_keys / items / properties / field / minLength
```
Added value: +1
```
addedOutput schema / properties / evidence / properties / join_keys / items / properties / field / type
```
Added value: +"string"
```

changedOutput schema / properties / evidence / properties / observed / properties / data_start / anyOf

Previous value: -[
-  {
-    "format": "date",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "format": "date",
+    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / evidence / properties / observed / properties / data_through / anyOf

Previous value: -[
-  {
-    "format": "date",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "format": "date",
+    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / evidence / properties / requested_scope / properties / end_date / anyOf

Previous value: -[
-  {
-    "format": "date",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "format": "date",
+    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedOutput schema / properties / evidence / properties / requested_scope / properties / filters / propertyNames
```
Added value: +{
+  "type": "string"
+}
```
removedOutput schema / properties / evidence / properties / requested_scope / properties / group_by / items / $ref
```
Removed value: -"#/properties/evidence/properties/tool"
```
addedOutput schema / properties / evidence / properties / requested_scope / properties / group_by / items / maxLength
```
Added value: +128
```
addedOutput schema / properties / evidence / properties / requested_scope / properties / group_by / items / minLength
```
Added value: +1
```
addedOutput schema / properties / evidence / properties / requested_scope / properties / group_by / items / type
```
Added value: +"string"
```
removedOutput schema / properties / evidence / properties / requested_scope / properties / sort / items / properties / field / $ref
```
Removed value: -"#/properties/evidence/properties/tool"
```
addedOutput schema / properties / evidence / properties / requested_scope / properties / sort / items / properties / field / maxLength
```
Added value: +128
```
addedOutput schema / properties / evidence / properties / requested_scope / properties / sort / items / properties / field / minLength
```
Added value: +1
```
addedOutput schema / properties / evidence / properties / requested_scope / properties / sort / items / properties / field / type
```
Added value: +"string"
```

changedOutput schema / properties / evidence / properties / requested_scope / properties / start_date / anyOf

Previous value: -[
-  {
-    "format": "date",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "format": "date",
+    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

Changed1 schema field changedNov 2, 2026

changedInput schema / properties / reason / description

Previous value: -"Filter by reimbursement reason (e.g. LOST_INBOUND, DAMAGED_WAREHOUSE)"New value: +"Filter by reimbursement reason, exact match on Amazon's report label (e.g. Lost_Warehouse, Lost_Inbound, CustomerReturn, Reimbursement_Reversal). Known Finances API spellings such as WAREHOUSE_LOST are accepted and translated."

Changed2 schema fields changedOct 28, 2026

changedInput schema / properties / end_date / description

Previous value: -"Optional. YYYY-MM-DD end date for approval_date."New value: +"Optional. YYYY-MM-DD end date for approval_date. The range may span at most 366 days."

changedInput schema / properties / start_date / description

Previous value: -"Optional. YYYY-MM-DD start date for approval_date."New value: +"Optional. YYYY-MM-DD start date for approval_date. The range may span at most 366 days."

Changed2 schema fields changedOct 27, 2026

changedInput schema / properties / include_diagnostics / description

Previous value: -"True may add expanded freshness diagnostics. Basic empty-result data-window diagnostics are included by default when available."New value: +"True enables expanded freshness diagnostics. Where supported, snapshot_capture_at and snapshot_data_through_date are populated only when include_diagnostics=true, in both compact and full-row modes; values may still be null if source data is unavailable. Default false. Basic empty-result data-window diagnostics are included by default when available."

changedInput schema / properties / include_raw_rows / description

Previous value: -"False returns compact rows. Default true."New value: +"For tabular results, false returns compact rows capped at MCP_TEXT_ROW_PREVIEW_LIMIT (default 10), regardless of limit. Complete-page and custom non-tabular responses may ignore this option; see tool-specific notes. Default true; large full-row responses are capped separately. Freshness fields require include_diagnostics=true in either row mode, where supported."

Changed5 schema fields changedOct 27, 2026

changedOutput schema / properties / evidence / properties / basis / properties / date / items / enum

Previous value: -[
-  "order_date",
-  "reporting_date",
-  "click_attribution_date",
-  "posted_date",
-  "settlement_date",
-  "snapshot_date",
-  "live_observation_time",
-  "event_time",
-  "effective_date",
-  "not_applicable",
-  "not_reported"
-]New value: +[
+  "order_date",
+  "reporting_date",
+  "click_attribution_date",
+  "posted_date",
+  "financial_event_group_start",
+  "settlement_date",
+  "snapshot_date",
+  "live_observation_time",
+  "event_time",
+  "effective_date",
+  "not_applicable",
+  "not_reported"
+]

changedOutput schema / properties / evidence / properties / entity_types / items / enum

Previous value: -[
-  "account",
-  "marketplace",
-  "product",
-  "variation_family",
-  "listing",
-  "offer",
-  "inventory_item",
-  "fulfillment_center",
-  "order",
-  "order_item",
-  "campaign",
-  "ad_group",
-  "ad",
-  "target",
-  "keyword",
-  "search_query",
-  "portfolio",
-  "store",
-  "audience_segment",
-  "dsp_advertiser",
-  "shipment",
-  "inbound_plan",
-  "fulfillment_operation",
-  "transaction",
-  "settlement",
-  "financial_event",
-  "return",
-  "reimbursement",
-  "promotion",
-  "review",
-  "catalog_definition",
-  "audit_event",
-  "not_applicable"
-]New value: +[
+  "account",
+  "marketplace",
+  "product",
+  "variation_family",
+  "listing",
+  "offer",
+  "inventory_item",
+  "fulfillment_center",
+  "order",
+  "order_item",
+  "campaign",
+  "ad_group",
+  "ad",
+  "target",
+  "keyword",
+  "search_query",
+  "portfolio",
+  "store",
+  "audience_segment",
+  "dsp_advertiser",
+  "shipment",
+  "inbound_plan",
+  "fulfillment_operation",
+  "transaction",
+  "settlement",
+  "financial_event",
+  "financial_event_group",
+  "return",
+  "reimbursement",
+  "promotion",
+  "review",
+  "catalog_definition",
+  "audit_event",
+  "not_applicable"
+]

changedOutput schema / properties / evidence / properties / join_keys / items / properties / entity_type / enum

Previous value: -[
-  "account",
-  "marketplace",
-  "product",
-  "variation_family",
-  "listing",
-  "offer",
-  "inventory_item",
-  "fulfillment_center",
-  "order",
-  "order_item",
-  "campaign",
-  "ad_group",
-  "ad",
-  "target",
-  "keyword",
-  "search_query",
-  "portfolio",
-  "store",
-  "audience_segment",
-  "dsp_advertiser",
-  "shipment",
-  "inbound_plan",
-  "fulfillment_operation",
-  "transaction",
-  "settlement",
-  "financial_event",
-  "return",
-  "reimbursement",
-  "promotion",
-  "review",
-  "catalog_definition",
-  "audit_event",
-  "not_applicable"
-]New value: +[
+  "account",
+  "marketplace",
+  "product",
+  "variation_family",
+  "listing",
+  "offer",
+  "inventory_item",
+  "fulfillment_center",
+  "order",
+  "order_item",
+  "campaign",
+  "ad_group",
+  "ad",
+  "target",
+  "keyword",
+  "search_query",
+  "portfolio",
+  "store",
+  "audience_segment",
+  "dsp_advertiser",
+  "shipment",
+  "inbound_plan",
+  "fulfillment_operation",
+  "transaction",
+  "settlement",
+  "financial_event",
+  "financial_event_group",
+  "return",
+  "reimbursement",
+  "promotion",
+  "review",
+  "catalog_definition",
+  "audit_event",
+  "not_applicable"
+]

changedOutput schema / properties / evidence / properties / join_keys / items / properties / role / enum

Previous value: -[
-  "account_id",
-  "marketplace_id",
-  "asin",
-  "advertised_asin",
-  "purchased_asin",
-  "child_asin",
-  "parent_asin",
-  "seller_sku",
-  "fnsku",
-  "order_id",
-  "order_item_id",
-  "campaign_id",
-  "ad_group_id",
-  "ad_id",
-  "target_id",
-  "keyword_id",
-  "search_query",
-  "portfolio_id",
-  "shipment_id",
-  "inbound_plan_id",
-  "operation_id",
-  "transaction_id",
-  "settlement_id",
-  "promotion_id",
-  "not_applicable"
-]New value: +[
+  "account_id",
+  "marketplace_id",
+  "asin",
+  "advertised_asin",
+  "purchased_asin",
+  "child_asin",
+  "parent_asin",
+  "seller_sku",
+  "fnsku",
+  "order_id",
+  "order_item_id",
+  "campaign_id",
+  "ad_group_id",
+  "ad_id",
+  "target_id",
+  "keyword_id",
+  "search_query",
+  "portfolio_id",
+  "shipment_id",
+  "inbound_plan_id",
+  "operation_id",
+  "transaction_id",
+  "financial_event_group_id",
+  "settlement_id",
+  "promotion_id",
+  "not_applicable"
+]

changedOutput schema / properties / evidence / properties / metric_families / items / enum

Previous value: -[
-  "sales",
-  "traffic",
-  "advertising",
-  "inventory",
-  "returns",
-  "reimbursements",
-  "fees",
-  "profitability",
-  "catalog",
-  "rank",
-  "fulfillment",
-  "pricing",
-  "promotions",
-  "reviews",
-  "audit",
-  "availability",
-  "not_applicable"
-]New value: +[
+  "sales",
+  "traffic",
+  "advertising",
+  "inventory",
+  "returns",
+  "reimbursements",
+  "payouts",
+  "fees",
+  "profitability",
+  "catalog",
+  "rank",
+  "fulfillment",
+  "pricing",
+  "promotions",
+  "reviews",
+  "audit",
+  "availability",
+  "not_applicable"
+]

AddedOct 7, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, non-destructive, and closed-world, so safety is covered. The description adds real behavioral context beyond that: seller-scoped storage needing a proved seller and region, legacy rows being paginated and never additive, marketplace_id being an import stamp rather than native attribution, and label-enrichment constraints. That is meaningful disclosure for a read tool.

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 core fetch sentence is front-loaded, but the remainder is dense and occasionally convoluted (e.g. 'never additive seller history', the import-stamp clause). Several sentences blend scope rules and attribution caveats in ways that take effort to parse, and some of this belongs in parameter descriptions rather than the tool blurb.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 11 parameters, a full output schema, and rich annotations, the description covers the tricky scope and attribution semantics an agent needs. Sorting and pagination are left to the schema, which is acceptable given an output schema and 100% param coverage.

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 100%, so every parameter is already documented, setting the baseline at 3. The description reinforces reason-label translation and record_scope ownership semantics, but much of its seller_id/marketplace_id discussion refers to returned fields, not the input parameters, so it adds only modest value over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource: 'Get FBA reimbursement records by date, ASIN or reason,' which immediately tells an agent what is returned and what can filter it. It doesn't name a sibling (e.g. get_financial_events or get_returns) it should be distinguished from, so it stops short of a 5.

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

Usage Guidelines3/5

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

It explains the fetch dimensions and the 'current' vs 'unattributed_legacy' scope choice, but never states when to prefer this tool over related siblings like get_financial_events or get_returns. Usage is implied by the resource name rather than explicitly routed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Agent Central tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.