export_acceptance_pack

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

With no annotations, the description carries the full burden and does so well: it discloses read-only semantics, that nothing is written/signed/executed, the three required environment settings, that the tenant comes from config and never from an argument, and the OK/REFUSED/UNAVAILABLE status model including that errors surface as UNAVAILABLE rather than fabricated data. It also states the API version prerequisite and the 'not a compliance finding' caveat; only per-status remediation is missing.

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?

Purpose and scope come first, followed by behavior, prerequisites and return statuses in a logical order. The environment-variable and status enumeration is dense but each clause carries operational meaning; only the phrasing is slightly compressed rather than padded.

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 a nested opaque request object, no annotations and an existing output schema, the description covers the operational essentials: read-only nature, required configuration, tenant resolution, and the tri-state return model. Remaining gaps are minor — what a REFUSED implies for the caller's next step, and any limits on case volume.

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 0% and the single `request` parameter is an untyped free-form object, so the description does real work by revealing that it carries one or more cases plus an optional control id and version. That is partial compensation only — the shape, field names and required contents of `request` remain undocumented in both places.

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?

Opens with a specific verb+resource pair ('Acceptance-pack export for one or more cases') and adds the optional control-id/version mapping, so an agent knows exactly what is produced. It does not name any sibling tool, so differentiation from the many other evidence/receipt tools is left to inference.

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 clearly frames this as a read-only view of records the caller supplies ('it writes, signs and executes nothing'), which implicitly tells an agent this is the non-mutating path. However, there is no explicit when-to-use versus alternatives guidance and no sibling is referenced, so the agent must infer its place among export/evidence tools.

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