Inspect a URL's metadata without downloading: retrieve file size, Range support, ETag, filename, and Content-Type to plan downloads and check compatibility.
探测 URL：返回文件大小、是否支持 Range（分片）、ETag、文件名、Content-Type。不下载。
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | 目标 URL，支持 http/https | |
| proxy | No | HTTP 代理，如 http://127.0.0.1:7890 | |
| headers | No | 附加请求头，如 Cookie/Referer | |
| insecure | No | 跳过 TLS 证书校验 |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It usefully discloses the returned fields and that no file content is fetched, but says nothing about redirect handling, failure behavior, auth/cookie implications beyond the headers param, or side effects of the network request.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with the return payload enumerated and the key non-download caveat at the end. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description correctly lists the returned fields, which is the essential information. Remaining gaps are error/redirect behavior for a tool that performs a live network fetch.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, including url, proxy, headers and insecure, so baseline is 3. The description adds no meaning beyond the schema for any of the four parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (探测/probe) and resource (URL) and enumerates exactly what is returned: file size, Range support, ETag, filename, Content-Type. The closing '不下载' (does not download) sharply separates it from the download-oriented siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'不下载' implicitly frames this as the metadata-only precursor to start_download/download_hls, giving clear context for selection. It never explicitly names a sibling or states when not to use it, so it stops short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.