Skip to main content
Glama

test_download_stream

Validate download streaming by sending ten data frames and optionally triggering an error frame; does not access QQ.

Instructions

测试下载流(推送 10 个数据帧,验证流式传输,不触达 QQ) 经 invoke_action 调用,仅测试传输,不访问 QQ。 Returns: 流式帧:data_chunk*10 → data_complete(error=true 时以 error 帧结束)

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": "test_download_stream"
  }
}

Input Schema

NameRequiredDescriptionDefault
errorNo是否触发测试错误

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 exact emission sequence (data_chunk x10 followed by data_complete, or an terminal error frame when error=true) and the no-QQ-contact guarantee, which is real behavioral context an agent cannot get from readOnlyHint/destructiveHint. Minor tension with openWorldHint=true is not a contradiction since the flag describes the integration family, and it still omits whether temp artifacts are left behind for clean_stream_temp_file.

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?

Two compact clauses with the purpose and the no-QQ constraint front-loaded, followed by the return sequence in parentheses. Dense but every element carries information; the mixed-language phrasing is slightly harder to parse than necessary.

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 one optional parameter, no output schema, and simple annotations, the description supplies enough: what it emits, how many frames, and how errors end the stream. The remaining gap is whether a temp stream file is created and must be cleaned up, which matters given the clean_stream_temp_file sibling.

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 coverage is 100% and the single `error` parameter is already documented in-schema, so the baseline is 3. The description adds only a light gloss that error=true causes the stream to terminate with an error frame, which is a small increment over 'whether to trigger a test error.'

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 concrete verb and resource ('测试下载流' – test download stream) and immediately qualifies the scope: pushes 10 frames, verifies streaming, and does not touch QQ. That scoping cleanly separates it in spirit from the real download_*_stream siblings without naming one, which keeps it just 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?

It tells the agent this is a test-only path invoked via invoke_action and that it does not access QQ, which implies 'use this instead of real downloads when you only want to verify streaming.' However, it never states when to prefer it, when it is unnecessary, or any prerequisite/side-effect conditions, so usage is only implied.

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