Skip to main content
Glama
Sign In

AdsTurbo

by io.github.AdsTurbo
OverviewDiscussionsAdmin

create_ad_from_product_url

贴商品链接出广告

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_ad_from_product_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
ad_typeNo广告类型。ugc：真人自拍口播种草，有口播，语言按 language；product_showcase：棚拍产品质感，默认只有配乐、没有口播。不传时按商品自动选型（第一视角上手、痛点演示、上身试穿等），可能没有口播，要口播请传 ugc。传 product 时必填 ugc 或 product_showcase，不传会被预检 60819 拒。
productNo已有商品数据；与 product_url 二选一。
durationNo仅支持 15 秒；传 0 或省略按 15 秒。
languageNo口播语言；不传时按输入内容识别，识别不到用 English。只有带口播的类型（如 ugc）会念出来。
resolutionNo分辨率，默认 720p。
product_urlNo公开商品页 URL；与 product 二选一。
aspect_ratioNo画幅，默认 9:16。
idempotency_keyNo可选幂等键（1–64 位字母、数字、_、-，建议 UUID）。超时重试时带同一个值：内容相同返回原 work_id、不重复扣积分；内容不同报 60822；上次失败已退款报 60823（换新键）；同键处理中报 429。

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

C2.2/5.0
Behavior2/5

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

The main description is silent on behavioral traits. Annotations already indicate a non-readonly, open-world, non-idempotent, non-destructive operation, but the description does not explain that this is an asynchronous job returning a work_id, that credits are pre-estimated or charged, or how retries and idempotency keys behave.

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

Conciseness2/5

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

The description is only seven Chinese characters and is front-loaded, but it is under-specified rather than concise. It omits the basic action, output type, and async nature that an agent needs before invoking the tool.

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

Completeness2/5

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

For a tool with eight parameters, nested product data, three enums, and an asynchronous work_id flow, the top-level description is far too sparse. The schema carries the missing detail, but the description itself does not explain the essential workflow or the product_url/product tradeoff.

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 description coverage is 100%, so all eight parameters, enums, and the nested product object are already documented in the schema. The description adds no parameter meaning beyond what the schema provides, so the baseline of 3 is appropriate.

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

Purpose2/5

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

The description '贴商品链接出广告' restates the tool name (create_ad_from_product_url) almost verbatim. It does not clarify that the output is a generated ad video, nor does it mention the product-data alternative or distinguish this from siblings like ad_clone_generate or video_generate.

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

Usage Guidelines2/5

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

The top-level description gives no guidance on when to use this tool versus alternatives. The schema description does add conditional usage (product_url vs product, fallback on scrape failure, follow-up via get_work_status), but that is structured schema content rather than tool-description guidance, and it still does not address sibling tools.

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

All AdsTurbo toolsInspect
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