get_download_task

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

With no annotations, the description carries the whole burden and does so well: it defines the in-progress vs terminal status sets, explains that items.success means the whole item finished, clarifies that completed_images includes cache hits and is not a network-transfer count, and notes the manifest is only final after the batch收尾. It does not cover error behaviour for unknown/expired task_ids, which keeps it from a 5.

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?

Front-loaded purpose sentence followed by compact, high-density notes on status sets and counter semantics; no filler. The enumerated status lists are slightly compressed and harder to scan than prose or a table would be, but nothing is wasted.

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?

An output schema exists, so return-field documentation is not required, and the description still adds the semantic layer (status lifecycle, meaning of success/unfinished_ids, what the manifest is). The only real gap is that an agent is never told how to obtain a task_id or that terminal status means further polling is pointless.

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?

The single required parameter task_id has 0% schema description coverage, and the description never explains it — not where the ID comes from (e.g. download_batch/start_download) nor whether it survives restarts, even though cross-restart reports are mentioned. The description's rich content is entirely about return semantics, so it fails to compensate for the coverage gap on the one input it takes.

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 — querying background download status, processed-image count, and the order-preserving manifest, plus reading the cross-restart task report. It is clearly distinguishable from siblings like cancel_download, retry_download and download_batch.

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?

Usage context is clear (poll progress / inspect a finished or interrupted batch) and it explicitly routes the agent onward: unfinished_ids can be fed to retry_download. It never states when NOT to use it or that polling is the intended pattern, so it stops short of full when/when-not guidance.

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