Skip to main content
Glama

download_file_stream

Streams files from local stream paths, URLs, or cached media and saves them to the MCP download directory through invoke_action, returning file info, chunks, and completion frames.

Instructions

以流式方式下载文件(stream 目录本地文件 / URL / 缓存媒体) 替换实际公开可访问地址;经 invoke_action 调用,文件保存到 MCP 下载目录。 Returns: 流式帧:file_info → file_chunk* → file_complete

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": "download_file_stream"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo文件路径(限 stream 临时目录)/ http(s) URL
file_idNo文件 ID(缓存的图片/语音 id)
chunk_sizeNo分块大小(字节,默认 64KB)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations, the description discloses the concrete side effect (the file is written to the MCP download directory — which also explains why readOnlyHint is false) and the exact emission protocol: file_info → file_chunk* → file_complete. That frame sequence is genuinely useful since no output schema exists. It omits auth requirements, size limits, and error/interruption behavior.

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?

Purpose is front-loaded, and the return-frame summary is on its own labeled line, which reads cleanly. One clause ('替换实际公开可访问地址') is vague and costs a little clarity, but overall there is little waste.

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 no output schema, the description carries the return-value burden and does so by naming the frame sequence and the save location. For a three-optional-parameter streaming tool this is close to complete; only error handling and how to reassemble chunks are left unstated.

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 the schema already documents file, file_id, and chunk_size (with its 64KB default). The description's mapping of source types onto 'file' vs 'file_id' is helpful framing but largely restates what the schema says, and chunk_size is never mentioned in the prose.

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 verb and resource ('以流式方式下载文件') and enumerates the accepted source types: stream temp-directory local files, http(s) URLs, and cached media. It also notes the file lands in the MCP download directory. It does not name any sibling (e.g. download_file, download_file_image_stream, download_file_record_stream) to disambiguate, 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?

Usage is only implied: pick this when you need chunked/streaming retrieval of a stream-dir file, a URL, or cached media, and call it via invoke_action. There is no explicit 'when not to use' and no pointer to plain download_file or the image/record stream variants for the cases they cover, leaving the agent to infer the boundary.

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

Deploy Server

Other Tools