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

Beyond the annotations, the description discloses that the tool returns a short-lived download capability, may enqueue a billed export when format conversion is needed, and that filters are stateless snapshots computed with DuckDB for parquet. It also tells the agent to repeat the same filter during status polling, which is essential behavioral context.

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 three tightly packed sentences with the main action and outcomes front-loaded. Each sentence adds distinct and useful information about return behavior, filtering, and polling, with no repetition or filler.

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 tool with a nested schema, no output schema, and no schema descriptions, the description covers the core workflow and filter semantics well enough to invoke it correctly. It is not fully complete on parameter-level details such as format options and expiration, but those are mostly discoverable from the schema itself.

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?

With 0% schema description coverage and a nested download object, the description adds useful meaning for the filter fields: bbox, typed attribute predicates, column projection, and row cap. However, it leaves several parameters undocumented, including sourceId, format enum details, and expiresIn behavior, so it only partially compensates for the schema gap.

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 states a specific verb and resource: prepare a dataset download. It clearly distinguishes the two outcomes (short-lived capability vs. billed export enqueue) and explains the optional filter snapshot behavior. This lets an agent separate it from the polling sibling source_download_status.

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 clear context for when conversion triggers a billed export and advises repeating the same filter when polling status. It does not explicitly name source_download_status as the alternative to use after preparation, and it states no when-not conditions, but the operational context is otherwise clear.

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