WisePPC

get_marketplace_data

Read-onlyIdempotent

One Amazon seller-marketplace object by resource (amazon_sp target). order_detail: one order or S01- MCF order, stored raw rows by block (items, shipments, returns, reimbursements, fees, promotions, change timeline), exact money strings; long blocks page with section + offset. aplus_content: A+ documents from a copy polled about daily. product_type_definitions: stored category schemas and their history. estimate_fees: live Amazon quotes, estimates not guarantees; action=fees (default) selling fees for 1-20 ASINs/SKUs at your price (cached 6h).

Input Schema

Name	Required	Description
`asin`	No	aplus_content: search only: 10-character uppercase alphanumeric ASIN; lists documents attached to it.
`fresh`	No	estimate_fees.
`items`	No	estimate_fees.
`action`	No	aplus_content: search\|get\|asins; product_type_definitions: search\|get\|versions\|changes; estimate_fees: fees (default).
`offset`	No	order_detail: Resume the section at next_offset.
`target`	No	From get_session_context targets: kind:account[:unit].
`asinSet`	No	aplus_content: asins only: nonempty filter of 10-character uppercase alphanumeric ASINs; omitted includes all attached ASINs.
`section`	No	order_detail: Block name or sections JSON-pointer key.
`currency`	No	estimate_fees: defaults to the marketplace's
`keywords`	No	product_type_definitions: search only: case-insensitive substring of type/display name, at most 200 characters.
`order_id`	No	order_detail: Amazon order id (111-1234567-1234567) or an S01- MCF id.
`pageSize`	No	aplus_content search/asins, product_type_definitions search/versions/changes: 1-100, default 20.
`resource`	Yes
`pageToken`	No	The previous nextPageToken (aplus_content) or nextToken (product_type_definitions); same action and filters.
`toVersion`	No	product_type_definitions: changes only, required: destination version's 32-character lowercase hex canonical hash.
`versionId`	No	product_type_definitions: get only: 32-character lowercase hex canonical hash; omitted selects latest captured.
`fromVersion`	No	product_type_definitions: changes only, required: source version's 32-character lowercase hex canonical hash.
`productType`	No	product_type_definitions: get/versions/changes: required Amazon product type name, at most 200 characters.
`schemaPointer`	No	product_type_definitions: get only: JSON Pointer selects a schema part. Omit for full schema; MCP errors if over budget, requiring a pointer. REST has no such cap.
`includedDataSet`	No	aplus_content: get/asins only. get defaults to CONTENTS+METADATA; body may be unavailable or older than metadata. asins defaults to ASINs only; METADATA adds relation details, CONTENTS has no effect.
`timeline_offset`	No	order_detail: Resume the timeline at its next offset.
`contentReferenceKey`	No	aplus_content: get/asins only, required: 1-100 letters, digits or hyphens.
`fba_shipment_sales_offset`	No	order_detail: Resume FBA shipment sales at its next offset.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedNov 4, 2026

changedInput schema / properties / action / description

Previous value: -"aplus_content: search|get|asins; product_type_definitions: search|get|versions|changes."New value: +"aplus_content: search|get|asins; product_type_definitions: search|get|versions|changes; estimate_fees: fees (default)."

changedInput schema / properties / action / enum

Previous value: -[
-  "search",
-  "get",
-  "asins",
-  "versions",
-  "changes"
-]New value: +[
+  "search",
+  "get",
+  "asins",
+  "versions",
+  "changes",
+  "fees"
+]

addedInput schema / properties / currency

Added value: +{
+  "description": "estimate_fees: defaults to the marketplace's",
+  "type": "string"
+}

addedInput schema / properties / fresh

Added value: +{
+  "description": "estimate_fees.",
+  "type": "boolean"
+}

addedInput schema / properties / items

Added value: +{
+  "description": "estimate_fees.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "asin": {
+        "type": "string"
+      },
+      "fba": {
+        "type": "boolean"
+      },
+      "id": {
+        "type": "string"
+      },
+      "price": {
+        "type": [
+          "number",
+          "string"
+        ]
+      },
+      "program": {
+        "enum": [
+          "FBA_CORE",
+          "FBA_SNL",
+          "FBA_EFN"
+        ],
+        "type": "string"
+      },
+      "shipping": {
+        "type": [
+          "number",
+          "string"
+        ]
+      },
+      "sku": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "price"
+    ],
+    "type": "object"
+  },
+  "maxItems": 20,
+  "minItems": 1,
+  "type": "array"
+}

changedInput schema / properties / resource / enum

Previous value: -[
-  "order_detail",
-  "aplus_content",
-  "product_type_definitions"
-]New value: +[
+  "order_detail",
+  "aplus_content",
+  "product_type_definitions",
+  "estimate_fees"
+]

AddedNov 2, 2026

TDQS

A4/5.0

Behavior5/5

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

Beyond the read-only and idempotent annotations, the description discloses important behavior: order_detail stores raw rows by block with exact money strings and section/offset paging, aplus_content comes from a copy polled about daily, and estimate_fees returns live estimates that are not guarantees and are cached for six hours.

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 description is dense but front-loads the overall purpose and then groups details by resource, with every phrase carrying useful information. It loses a point for being a single semicolon-heavy paragraph that is less scannable than it could be.

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?

For a 23-parameter multiplexer with four resources, the description covers all modes and important quirks such as paging, freshness, caching, and estimate reliability. It does not describe the return envelope or some output shapes, but the rich schema and annotations cover much of that gap.

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 96%, so the schema already documents nearly every parameter. The description still adds cross-parameter meaning by explaining section plus offset paging for order_detail, the estimate_fees action default and item limit, and the caching behavior tied to that resource.

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?

The description states a specific Amazon seller-marketplace data retrieval tool and enumerates four resource modes with concrete contents. It is clear what the tool returns, though it does not explicitly distinguish itself from the generic sibling tools.

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?

The per-resource descriptions imply when each mode is useful, such as order_detail for stored order rows and estimate_fees for live fee quotes. However, there is no explicit guidance on when to use this tool versus alternatives like query or get_report, and no exclusions are stated.

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

All WisePPC 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.

Resources

Need Help?