Download a finished report (CSV)

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

Annotations already establish readOnly, idempotent, non-destructive behavior, so the bar is lower, and the description still adds real operational detail: the X-Content-SHA256 response header for integrity verification and the two concrete failure modes with status codes (409 report_not_ready, 409 report_expired). It does not say what the body looks like on failure or how long before expiry, but the added context is well beyond the annotations.

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 content is front-loaded and short, but the first line duplicates the title verbatim and the second sentence restates it a third time ('Download a finished report as CSV'). The error-state and header information is valuable; the repeated framing is not.

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 read tool with no output schema, the description covers the essential behavior an agent needs: the returned payload is CSV, the hash is available in a header for verification, and both blocking conditions return 409. Only minor gaps remain, such as whether the hash header is mandatory or how long an expired report retained.

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 100%, so the single `id` parameter is already documented as `rpt_…`; the description adds nothing about the identifier's meaning beyond implying it must reference a completed report. Baseline 3 is appropriate when the schema carries the parameter documentation.

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 gives a specific verb and resource ('Download a finished report as CSV'), which clearly separates the file-fetch action from metadata siblings like get_report and list_reports. It stops short of naming those siblings explicitly, so the differentiation is inferable rather than stated.

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 word 'finished' plus the two 409 cases implies the precondition (report must be completed before download) and tells the agent what happens otherwise. There is no explicit routing guidance such as 'use get_report for metadata, this tool for bytes', leaving the agent to infer the boundary with get_report and create_report.

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