start_download

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

With no annotations, the description carries the full disclosure burden. It does add real behavioral context: the operation is asynchronous, it returns a task id, and it supports resume. However, for a 14-parameter mutation-ish operation it says nothing about proxy/auth requirements, rate-limit effects, what happens on a failed checksum, or whether an existing output file is overwritten.

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?

Three short sentences, zero filler, and the core action is front-loaded before the async/return-value detail. Each sentence earns its place. It is arguably thin for the tool's complexity, but that is a completeness issue rather than a structure issue.

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?

This is a 14-parameter tool with no annotations, no output schema, and several tuning knobs (connections, limit_bps, dynamic_chunks, verify_seam, open_range) whose interactions matter. The description covers only async, task-id return, and resume, leaving the agent without enough context to configure or reason about the call. It does correctly disclose the return value, which partially offsets the missing output schema.

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 71%, so most parameters are already documented in the schema and the baseline is 3. The description only echoes one parameter ('支持断点续传' ↔ resume) and adds no syntax, defaults, or interaction guidance beyond that. It neither compensates for the undocumented proxy/headers/insecure params nor extends the documented ones.

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 and resource ('启动一个分片多连接下载任务'), and adds two meaningful qualifiers: async execution and multi-connection chunking. It names download_status as the progress-tracking companion, so an agent can place it in the workflow. It does not, however, distinguish itself from download_hls or queue_add, which are plausible alternatives for starting a transfer.

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?

The description implies usage ('start a download task') and points to download_status for progress, which is helpful routing. But it never says when to pick this over download_hls or the queue_add/queue_run pair, nor does it state prerequisites or when a task should be cancelled instead. Usage is implied rather than specified.

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