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

Adds real behavior beyond the annotations: previews of unpaid jobs are truncated to the first pages, output is draft-marked, and the returned link expires after 1 hour. Annotations only declare the non-read-only/non-idempotent/non-destructive profile; the description supplies the cost, truncation and expiry semantics that matter for planning.

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, front-loaded with what the tool returns and immediately followed by the constraints (partial pages, draft marking, 1-hour link). No 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?

Covers the output (download link) and its lifetime, but for an 8-parameter tool with a nested object and no output schema it says nothing about the DATEV-header/MT940-balance requirements for anonymous or balance-less statements, nor about whether a preview can be re-requested for the same job (annotations mark it non-idempotent). Adequate but with clear gaps.

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 100%, with enums and the nested DATEV object fully documented, so the description need add nothing. It mentions no parameter at all, leaving format, file_id and the DATEV/MT940 arguments entirely to the schema — acceptable baseline, no added value.

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?

States a specific resource (a preview of the job output) and its distinguishing traits: free, partial for unpaid jobs, watermarked as draft. It never names the clear sibling contrast (download_result returns the real deliverable), so differentiation is implied rather than asserted.

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?

Usage is inferable from 'free preview ... draft so it is not imported by mistake', which hints this is the pre-purchase inspection path, but there is no explicit when-to-use/when-not and no alternative tool is named for the full result.

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