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

No annotations are provided, so the description carries the full burden; it does disclose the non-clinical, evaluation-only contract and the three output formats, which is meaningful behavioral context. It omits operational traits an agent needs: required permissions, whether export is synchronous, size limits, and whether an incomplete run can be exported.

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 function sentence is efficient and front-loading is reasonable, but four sentences of near-repetitive medical disclaimer precede it ('Not for clinical use' and the diagnose/treat/prescribe prohibition say largely the same thing). Roughly half the text is redundant boilerplate relative to the single operative sentence.

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?

With no output schema and no annotations, the description must cover more than it does; it handles formats and safety scope but says nothing about what the export returns (file path, URL, inline payload), success/failure conditions, or prerequisites on run state. Adequate for a simple two-parameter tool, 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 0%, so the description must compensate; it does partially by explaining the fmt values and what each format contains (full audit vs one-page PDF). run_id is left entirely unexplained — no statement that it must reference an existing verification run or its expected format.

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 verb (export) and resource (a run) and enumerates the three output artifacts: csv, pdf (full audit), and report (one-page committee PDF). It is distinguishable from read-only siblings like get_verification, though the format named 'report' overlaps conceptually with get_exam_report, which the description never addresses.

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?

Provides strong usage constraints — not for clinical use, testing/evaluation only, synthetic test data only — but these are scope restrictions rather than routing guidance. It never says when to choose export_verification over get_verification or get_exam_report, nor whether the run must be finished before exporting.

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