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

Adds real behavior beyond the annotations: download-time revalidation of 'evidence, revisions, access and expiry', the reproducibility guarantee of 'exact approved versions', and the downstream boundary that no buyer submission is triggered. Annotations already declare non-readonly/idempotent/no-destruct, so this context is a genuine supplement.

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?

Four short, front-loaded sentences with no filler; purpose comes first, then prerequisites, then behavior. 'Download rechecks evidence, revisions, access and expiry' is slightly telegraphic but earns its place.

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 six-parameter, nested-object mutation with no output schema and 17% schema coverage, the description covers the preconditions and revalidation flow but leaves the shape and meaning of documents/selection/planRevision largely to the schema. Adequate but with clear gaps for a tool of this complexity.

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 only 17%, so the description must compensate, and it only partially does. It maps loosely to concepts (approved versions -> documents/selection, final pack confirmation -> packConfirmationId, current file reviews -> per-document confirmationId), but the nested revision objects (outputJobId/payloadHash), planRevision, and the accepted/rejected selection arrays remain unexplained.

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?

Specific verb + resource combination ('Export the exact approved file versions and hash manifest as a ZIP') that an agent can act on. It is distinguishable from pack-adjacent siblings like output_download and export_dossier by the 'exact approved versions + hash manifest' scope, though it never names a sibling explicitly.

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?

Gives clear preconditions ('Requires current file reviews and final pack confirmation') and an explicit exclusion ('No automatic buyer submission'), which tells the agent this is not a submission step. It stops short of naming alternative export/download tools the agent should consider instead.

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