download

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

The description discloses important behaviors beyond the destructiveHint annotation: it explicitly states that files are overwritten ('overwriting the same path') and that probe=True performs a dry-run without saving ('probe checks without saving'). It also describes the return format (files with path, version, etc.). These details add value beyond the annotations, though it doesn't cover authentication or error cases.

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 is a single dense paragraph mixing Korean and English, which is a bit cluttered but front-loaded with the core purpose. It contains some redundancy (both languages for the same idea) and could be tightened, but it's not excessively long. The structure is acceptable but not exemplary.

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?

Given the tool has an output schema, the description still covers the main behavior, parameter semantics, and return details. It explains the overwriting behavior and probe mode, which are crucial for safe usage. It lacks guidance on when to use this tool vs siblings, which prevents a perfect score, but overall it's reasonably complete for a download operation.

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 must explain parameters, and it does for most: version/all_versions (mutually exclusive choice), out (destination directory, with default), utf8 (CSV UTF-8 conversion), and probe (dry-run). It doesn't explicitly explain dataset_id, but that's the required identifier and is fairly obvious from context. It also mentions the special case of STD_FILE being saved as a full CSV, adding nuance.

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 clearly states the tool's primary action: saving originals locally ('Save originals locally'). It also notes overwriting behavior, which is a specific detail. However, it doesn't differentiate this tool from sibling tools like 'fetch' or 'get', which might also retrieve files, so it loses a point for lacking sibling differentiation.

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 gives parameter-level guidance (e.g., 'choose version or all_versions') but provides no guidance on when to use this tool versus alternatives. It doesn't mention any exclusion criteria or conditions that would route an agent to a sibling tool. This is a significant gap for a tool with many siblings.

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