download

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

Annotations already declare non-read-only, non-destructive, non-idempotent, open-world; the description adds meaningful behavior on top: existing local names are skipped (so re-runs are partially safe), the operation is asynchronous and must be polled, and expected_sha256 covers only a single file. Missing is any mention of auth requirements, concurrency, or what the returned task handle looks like.

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?

Four short sentences, each carrying distinct information (action, skip behavior, checksum option, next step), with the action front-loaded. No filler, though the telegraphic phrasing borders on under-specified rather than merely terse.

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?

Output schema exists, so return values need no explanation, and the async/polling lifecycle is covered. But for a tool with 5 params, 0% schema coverage, and no annotations about where files land, leaving mode and destination-directory semantics unexplained is a real completeness gap.

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 0%, so the description carries the full burden for five parameters, yet it only illuminates expected_sha256 (scoped to "one downloaded file"). The three-way mode enum, local_dir's default/target semantics, and rate_limit_bps are left entirely undocumented in both schema and description.

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?

Opens with a specific verb+resource ("Start downloading one Netdisk file/folder"), which separates it cleanly from upload, list_files, and file_info. The scope word "one" and the async framing ("Start") are precise. Differentiation from siblings is implicit via the obvious download/upload split rather than explicit naming.

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?

"Poll task_status to completion" gives a concrete follow-up action and effectively names the sibling tool to use next, which is real workflow guidance. However, the tool's central usage decision — when to pick mode locate vs pcs vs stream — is not addressed, and there are no stated preconditions or exclusions.

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