download_async_report_tool

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

There are no annotations, so the description carries the behavioral burden. It clearly indicates a non-destructive download action and reveals the return payload ('report rows'). It does not mention retention windows, size limits, or whether the downloaded data is consumed/one-time, but for a straightforward async download step the transparency is adequate.

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 short, front-loaded lines with no filler. The critical precondition is bolded for visibility, and the return statement is minimal but sufficient.

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 an output schema, the description covers the main contract: what to call, when to call it, and what it returns. The missing context around advertiser_id and download-specific caveats is minor but keeps this from being fully complete.

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 needed to compensate. It clarifies what task_id refers to, but it never explains advertiser_id or how the two IDs relate. The names are fairly self-explanatory and consistent with sibling advertiser-scoped tools, but a clear semantic gap remains.

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 uses a specific verb ('downloads') and a clear resource ('completed data for an async report task'), and states the output ('report rows'). It also distinguishes itself from the status-checking sibling check_async_report_tool by framing this as the follow-up data-fetching step.

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 an explicit, unambiguous condition: only call after check_async_report_tool returns status COMPLETE. This directly tells the agent when the tool is appropriate and prevents premature calls. No alternative download tool exists among the siblings, so no further exclusions are needed.

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