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

No annotations are supplied, so the description carries the full burden and does so: it discloses the exact state change (status flips to archived, lists and attachments hide it, bucket bytes and join rows stay), the failure mode folder_not_empty, the required permission memory:delete, and that the operation is reversible in spirit because no bytes are purged.

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 lead sentence front-loads verb and resource; subsequent sentences each add a distinct fact (state change, folder constraint, return shape, permission, non-purge, sibling pointer) with no repetition. Length is justified by the density of new information.

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 one-parameter mutation with no annotations, the definition covers everything an agent needs: effect, constraint, error surfaces, permission requirement and sibling routing. Return values are stated even though an output schema exists, which is mild redundancy rather than a gap.

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% and the single parameter is already described as a 'Storage object or folder UUID', so the baseline is 3. The description adds meaning by spelling out the divergent behaviour of that same id depending on whether it names a file or a folder, and by defining the not_found outcome for an unknown or already-archived id.

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+scope ('Soft-archive a Storage file or an empty Storage folder') and explicitly distinguishes itself from the purge case and from the sibling file_archive. An agent can tell it apart from storage_unlink, storage_move and file_archive without opening any schema.

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?

States the preconditions (folder must be empty, archive never cascades), the remediation path (move or archive children first), the negative case (not a purge; no hard delete of Storage objects) and the explicit alternative for shared-file documents (file_archive). When-to-use and when-not-to-use are both covered.

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