Skip to main content
Glama

download_file

Downloads a file from a URL or base64 data to the server's data/downloads temporary directory and returns the stored server path, not a local MCP host path.

Instructions

下载文件(url 或 base64)到 data/downloads 保存到 SnowLuma 服务端临时目录,返回服务端路径;不是 MCP 主机下载路径。 Returns: { file }

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNo
nameNo
base64No
headersNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

The annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: it clarifies that the write lands in a server-side temporary directory (implying ephemerality) and that the returned path is server-side rather than host-side, which is exactly the kind of ambiguity an agent would otherwise get wrong. It does not mention expiry or permissions, but against the annotation baseline this is solid.

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 purpose and the server-vs-host distinction are front-loaded and the wording is tight. The trailing '返回服务端路径' and 'Returns: { file }' partially duplicate each other, which is minor waste but not confusing.

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

Completeness3/5

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

With no output schema, zero schema coverage on four parameters, and no annotations describing return shape, the description covers the biggest risk (server-side vs host path) but leaves name, headers, and dual-source conflict handling unexplained. Adequate to call the tool, not complete.

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 0% across four parameters, so the description must compensate. It explains that the source is either a url or a base64 payload, adding real meaning to those two fields, but it is silent on 'name' and 'headers' and does not state precedence if both url and base64 are supplied. Partial compensation only.

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 (下载/download) and resource (file), and it specifies the destination as data/downloads on the SnowLuma server-side temporary directory. The explicit contrast '不是 MCP 主机下载路径' (not the MCP host path) makes the tool's scope unambiguous and meaningfully distinguishes it from the stream/download variants in the sibling list, though it never names those alternatives directly.

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 description tells the agent what inputs are acceptable (url or base64), which implies when the tool applies, but it provides no explicit exclusions or comparisons to siblings such as download_file_stream or download_file_image_stream. An agent must infer which download tool to pick from the name alone.

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