Product Description Generator

Generate product descriptions from writing instructions and product images. Call the Product Description Generator API via REST or MCP with a Nexscope API key.

CostRecent 10 credits / call

Try online

POST · https://api.nexscope.ai/ai/productDescriptionGeneratorMCP · nexscope_product_description_generator

What this API does

Generate product descriptions from writing instructions and product images. The request accepts operation, prompt, imageUrls, thinkingLevel, model. Its documented result includes completionTokens, content, dataSnapshotMonth, page, pageItemCount, pageSize, promptTokens, sourceTool.

Product Description Generator API use cases

Inspect a candidate product

To inspect a candidate product, a marketplace analyst submits operation and prompt to Product Description Generator. The returned completionTokens, content, dataSnapshotMonth help inspect the documented attributes of the candidate product.

Compare listing details

A marketplace analyst uses Product Description Generator with operation and prompt to compare listing details. The returned completionTokens, content, dataSnapshotMonth help compare product details with another shortlisted listing.

Prepare product evidence for a sourcing review

For this workflow, a marketplace analyst calls Product Description Generator with operation and prompt to prepare product evidence for a sourcing review. The result helps record product facts before a sourcing discussion.

Product Description Generator API FAQ

What does the Product Description Generator API return?

Generate product descriptions from writing instructions and product images. The documented output includes completionTokens, content, dataSnapshotMonth, page, pageItemCount, pageSize, promptTokens, sourceTool. It corresponds to the supplied operation, prompt, imageUrls, thinkingLevel, model. Optional fields can be absent; a missing value should not be interpreted as a measured zero. Example values illustrate the response shape, rather than live account results.

How many credits does the Product Description Generator API cost?

The current documented cost is Recent 10 credits / call. This is the same cost shown at the top of this page. If a range or estimate is displayed, the final charge depends on the request. Review your available credits and the pricing page before calling the API, and check API usage records for the actual charge.

How do I call the Product Description Generator API from my app or an MCP client?

Send a POST request to https://api.nexscope.ai/ai/productDescriptionGenerator with your API key as a Bearer token and the JSON inputs shown in API integration. In a compatible MCP client such as Claude or Cursor, connect Nexscope and call nexscope_product_description_generator. Use the MCP arguments shown in the MCP guide, or switch Online test to MCP to review its request before adding it to your app.

View plans and credits Connect this API with MCP

Try this API

Endpoint

https://api.nexscope.ai/ai/productDescriptionGenerator

MCP method

nexscope_product_description_generator

Step 1 of 3 · Authenticate

Authentication

All run endpoints require a user API key. Send it as a bearer token in the Authorization header.

Authorization: Bearer nk-xxxxxxxxxxxxxxxxx

Missing or invalid API keys return an authentication error. Manage keys from .

Step 2 of 3 · Send a request

POSThttps://api.nexscope.ai/ai/productDescriptionGenerator

Run an API

Use operation=query with the provider taskId returned by create. Query is sent to the API's /aigc/textTaskQuery endpoint; the system task-result endpoint is not used.

Example request

Replace YOUR_API_KEY, then run this command in your terminal.

curl -X POST 'https://api.nexscope.ai/ai/productDescriptionGenerator' \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "imageUrls": [],
  "model": "GEM_3_FLASH",
  "operation": "create",
  "prompt": "Write a product description for a wireless speaker.",
  "thinkingLevel": "minimal"
}'

Code example

{
  "imageUrls": [],
  "model": "GEM_3_FLASH",
  "operation": "create",
  "prompt": "Write a product description for a wireless speaker.",
  "thinkingLevel": "minimal"
}

Step 3 of 3 · Inspect the result

Check the response

Read code for the request status and data for the result. Open the parameter and response reference for the full field definitions.

HTTP status codes

Code	Description
200	Default HTTP response for both success and many business errors. Only outer JSON code 0 indicates success or asynchronous acceptance; inspect data for the result.
429	Execution admission rate limit; honor Retry-After when present.
503	Execution admission is temporarily unavailable; honor Retry-After when present.
Opt-in	X-Nexscope-Http-Status: semantic maps controller-handled business errors to HTTP status on run and task routes. Pre-authentication failures, such as a missing or invalid API key (code 11209, including an incomplete or corrupted copy) or an expired website login session (code 12001), may still return HTTP 200 before this mapping. Always check the outer JSON code; malformed requests and infrastructure failures may also return non-200 HTTP responses.

View parameters & response Try online

All categories/ AI Content Generation

POSThttps://api.nexscope.ai/ai/productDescriptionGenerator

Run this API

Send a JSON request to execute this API and receive the documented response payload.

Open tester

Endpoint

Method	`POST`
Path	`https://api.nexscope.ai/ai/productDescriptionGenerator`
Auth	`Bearer API key`
Content-Type	`application/json`

Request parameters

Name	Type	Required	Description
`operation`	`string`	optional	create (default) or query. Example: create
`prompt`	`string`	conditional	Product-copy generation instruction; required by create. Example: Write a product description for a wireless speaker.
`imageUrls`	`array`	optional	Media URLs used as context. Pass an empty array for text-only generation; use up to 10 images or typically one video. Example: []
`thinkingLevel`	`string`	conditional	Reasoning level required by create. GEM_3_1_PRO does not support minimal. Example: minimal
`model`	`string`	optional	Text-generation model. GEM_3_FLASH is the default. Example: GEM_3_FLASH
`memberId`	`string`	optional	Optional provider member identifier used by create and query. Example:
`taskId`	`string`	conditional	Provider task ID returned by create; required by operation=query. Example: 123456789

Response example

Platform response envelope. code 0 indicates success or acceptance; data contains the business result.

{
  "code": 0,
  "cost": "-1",
  "data": {
    "completionTokens": 350,
    "content": "Example product description.",
    "costToken": 1,
    "promptTokens": 120,
    "status": "PROCESSING",
    "taskId": "123456789",
    "totalTokens": 470
  },
  "msg": "Generation failed.",
  "time": "2026-01-01 00:00:00",
  "traceId": null,
  "ts": "0"
}

Response fields

Name	Type	Required	Description
`code`	`integer`	required	0 means accepted or successful; nonzero is a platform error.
`cost`	`string`	required	Elapsed milliseconds, never credits; -1 outside web requests.
`data`	`any`	required	Data value used by this API operation.
`msg`	`string \| null`	required	Msg value used by this API operation.
`time`	`string`	required	Server local time: yyyy-MM-dd HH:mm:ss.
`traceId`	`string \| null`	required	Trace id value used by this API operation.
`ts`	`string`	required	Epoch milliseconds.

Any of option 1

Name	Type	Required	Description
`data`	`object`	required	Data value used by this API operation.
`data.completionTokens`	`integer`	optional	Output token count when the task succeeds. Example: 350
`data.content`	`string`	optional	Generated product copy when the task succeeds. Example: Example product description.
`data.costTime`	`integer`	optional	Execution time reported by the upstream provider. Example: null
`data.costToken`	`integer`	optional	Provider-reported token cost. Example: 1
`data.dataSnapshotMonth`	`string`	optional	Data snapshot month returned by the upstream provider. Example: null
`data.page`	`integer`	optional	Current page returned by the upstream provider. Example: null
`data.pageItemCount`	`integer`	optional	Item count on the current page returned by the upstream provider. Example: null
`data.pageSize`	`integer`	optional	Page size returned by the upstream provider. Example: null
`data.promptTokens`	`integer`	optional	Input token count when the task succeeds. Example: 120
`data.sourceTool`	`string`	optional	Provider-specific source tool name. Example: null
`data.sourceType`	`string`	optional	Provider-specific source platform type. Example: null
`data.status`	`string`	optional	Task status such as PROCESSING, SUCCESS, or FAILED. Example: PROCESSING
`data.taskId`	`string`	optional	Asynchronous generation task ID. Example: 123456789
`data.title`	`string`	optional	Provider-specific response title. Example: null
`data.totalPage`	`integer`	optional	Total page count returned by the upstream provider. Example: null
`data.totalTokens`	`integer`	optional	Total token count when the task succeeds. Example: 470
`data.type`	`string`	optional	Provider-specific render or payload type. Example: null

Any of option 2

Name	Type	Required	Description
`data`	`null`	required	Data value used by this API operation.

Responses

Code	Description
200	Default HTTP response for both success and many business errors. Only outer JSON code 0 indicates success or asynchronous acceptance; inspect data for the result.
429	Execution admission rate limit; honor Retry-After when present.
503	Execution admission is temporarily unavailable; honor Retry-After when present.
Opt-in	X-Nexscope-Http-Status: semantic maps controller-handled business errors to HTTP status on run and task routes. Pre-authentication failures, such as a missing or invalid API key (code 11209, including an incomplete or corrupted copy) or an expired website login session (code 12001), may still return HTTP 200 before this mapping. Always check the outer JSON code; malformed requests and infrastructure failures may also return non-200 HTTP responses.

Data source, freshness, and limitations

Source, freshness, coverage, rate limits, and estimation notes are not specified in this API definition unless they appear in the request or response field documentation above. Do not assume official marketplace data or real-time freshness when it is not explicitly documented.

Step 1 of 2 · Connect your MCP client

MCP

V2 recommended

Connect remote agents through the standard MCP 2025-11-25 Streamable HTTP endpoint. Use OAuth 2.1 Authorization Code with PKCE, or an API key for compatibility.

POST https://api.nexscope.ai/mcp
MCP-Protocol-Version: 2025-11-25
Content-Type: application/json

Authentication

OAuth clients request the mcp:tools scope. The endpoint's 401 response advertises protected-resource metadata for authorization discovery.

Step 2 of 2 · Call the tool

Call a tool

{
  "jsonrpc": "2.0",
  "id": "tool-call-1",
  "method": "tools/call",
  "params": {
    "name": "nexscope_product_description_generator",
    "arguments": {
      "imageUrls": [],
      "model": "GEM_3_FLASH",
      "operation": "create",
      "prompt": "Write a product description for a wireless speaker.",
      "thinkingLevel": "minimal"
    }
  }
}

Legacy MCP v1

Existing API-key clients can continue using the compatibility endpoint. New integrations should use MCP v2.

GET / POST /mcp/legacy

What can you do with this API?

Data explained and practical use cases

AI Guide

Question

What can Product Description Generator produce, and how might I use it?

AI answer

Product Description Generator creates product-copy text from a writing prompt, with optional image or video context. Use operation=create to start generation and operation=query with the returned task ID to check it. The example combines status: PROCESSING, sample content, and a failure message, so treat it as a shape illustration and rely on the actual task status and result before using the copy. API documentation.

Data category	Documented fields	What the values mean
Generated copy	`data.content`	Product-description text when generation succeeds; this is the usable writing output.
Generation state	`data.status`	Indicates whether the task has finished successfully before the copy is used.
Input usage	`data.promptTokens`	Tokens used for the prompt and supplied context, when reported.
Output usage	`data.completionTokens`, `data.totalTokens`	Tokens in the generated completion and total token usage, when reported.

Draft a wireless-speaker description from a prompt listing its verified features.
- Prompt example: “I am researching products for an online store. Could you draft a wireless-speaker description from a prompt listing its verified features? Show the relevant returned evidence and tell me what input you need from me.”
Supply product photos as context and review the completed copy against those photos before adding it to a listing.
- Prompt example: “I am researching products for an online store. Could you supply product photos as context and review the completed copy against those photos before adding it to a listing? Show the relevant returned evidence and tell me what input you need from me.”
Generate alternative copy by changing the prompt's audience or tone, then compare the completed drafts.
- Prompt example: “I am researching products for an online store. Could you generate alternative copy by changing the prompt's audience or tone, then compare the completed drafts? Show the returned values behind the comparison, and mark missing data.”
Use reported token counts to understand how much input and output a generation used.
- Prompt example: “I am researching products for an online store. Could you use reported token counts to understand how much input and output a generation used? Show the relevant returned evidence and tell me what input you need from me.”

Data Example

Sample request and response

Request parameters

{
  "operation": "query",
  "taskId": "2549906"
}

Response

{
  "code": 0,
  "msg": null,
  "data": {
    "promptTokens": 441,
    "taskId": "2549906",
    "content": "```json\n{\n  \"sufficient\": false,\n  \"steps\": [],\n  \"missingInstructions\": \"Ürün açıklamasında ürünün özellikleri, faydaları ve hangi köpek türleri için uygun olduğu belirtilmiş; ancak ürünün nasıl kullanılacağına dair (örneğin: kullanım sıklığı, temizleme talimatı veya gözetim altında tutulması gibi) herhangi bir uygulama adımı veya kullanım talimatı bulunmamaktadır.\"\n}\n```",
    "completionTokens": 97,
    "status": "SUCCESS",
    "points": 0
  }
}