tnd_start_download

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

With no annotations, the description usefully discloses that starting a download creates an asynchronous task requiring subsequent polling. It does not cover duplicate or already-running tasks, failure behavior, or how the job identifier and eventual result are obtained.

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?

The description front-loads the action, then succinctly covers optional scoping and the required follow-up. It contains no filler or unnecessary repetition.

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?

For a three-parameter tool with a fully described schema, it adequately explains the basic call sequence. However, with no annotations or output schema, the missing default behavior when no range is supplied, lack of sibling differentiation, and absent job-result details are meaningful gaps.

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 coverage is 100%, and the schema already documents book_id, the 1-based range bounds, and the requirement to provide both range values together. The description only reinforces that specifying a range is optional, so the high-coverage baseline of 3 applies.

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?

The description gives a clear verb and resource—“启动下载器的下载任务”—and adds that a chapter range can be selected. It does not explain how this general range-based starter differs from tnd_start_book_download, tnd_start_chapter_download, or tnd_start_discrete_downloads.

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?

It provides concrete usage context: range_start/range_end optionally narrow the chapter range, and tnd_wait_job must be polled after the task starts. This is actionable workflow guidance, but there is no rule for choosing among the sibling download starters or any explicit exclusion.

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