download_dataset

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

With no annotations, the description carries the behavioral burden. It discloses that the operation is local-only and performs no remote fetch, signaling a safe, non-destructive read. It does not mention auth or failure behavior, but the output schema covers return structure and this is a simple availability report.

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?

Two short sentences state the core operation, the exactness requirement, and the local-only behavior. No filler, redundant restatement of the tool name, or duplication of schema details.

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 single-parameter, output-schema-backed tool, the description covers the essential selection and invocation concerns: exact dataset_id, local-only behavior, and that no remote fetch occurs. The only minor gap is the mismatch between the tool name ('download') and its report-only behavior, which the description partially mitigates.

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 schema fully documents dataset_id with the exact canonical constraint and examples, so schema coverage is complete. The description adds only the local-only context and does not materially extend the parameter semantics beyond the schema.

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 operation ('Report local raw snapshot availability') and the target resource ('an exact dataset_id'), and the 'Local-only; no remote fetch' qualifier differentiates it from fetch/materialization tools. It does not explicitly name sibling tools, but the purpose is unambiguous.

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 when to use the tool (when checking local availability of an exact dataset_id) and rules out remote fetching, but it does not provide explicit when-not-to-use guidance or point to alternatives among the listed siblings.

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