Download + validate report data

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

Annotations already provide readOnlyHint=true. The description adds valuable behavioral context: decompression, integrity checks, server-side totals, and the saveAs mechanism to avoid dumping large datasets into chat. It also instructs to present reconciled totals, which is critical for proper agent usage.

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 concise and front-loaded, starting with the core purpose and then detailing behavioral notes. Every sentence serves a purpose, though it could be slightly tightened without losing information.

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 no output schema, the description covers the return format (totals and row sample) and explains the validation checks. It also addresses large result set handling. Missing some error handling details, but overall sufficient for an agent to use correctly.

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 coverage is 75%, with most parameters having descriptions. The description adds context that saveAs avoids dumping into chat and maxRowsInline controls inline rows, but it does not explicitly describe profileId or the default behavior. Overall, it adds marginal value 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 tool downloads a completed report, decompresses it, runs data-integrity checks, and returns reconciled totals with a row sample. It explicitly distinguishes itself from siblings like create_report and get_report_status by focusing on completed reports and validation.

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 explicitly states the report must be COMPLETED, which guides when to use this tool. It does not directly name alternatives, but the context of 'completed' implies it should be used after get_report_status indicates completion, making usage clear.

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