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

Adds real context beyond the annotations: no media or feedback is deleted, feedback stays attached to its version, new assets inherit folder and sharing, and partial failures are not rolled back ('earlier ones are not undone if a later one fails'). The annotations cover non-destructive/idempotent, and the description confirms rather than contradicts them, though it doesn't state auth/permission requirements for a mutating tool.

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?

Front-loads the mutation and its result, then packs invariants, undo path, and failure semantics into short declarative clauses with zero filler. Every sentence carries a distinct fact an agent needs.

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?

No output schema exists, and the description compensates by naming the already_separate status and explaining per-version, non-transactional results. Combined with the annotations, an agent has everything needed to invoke this correctly.

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% for the single parameter, so the schema already documents version_ids; the baseline of 3 applies. The description adds per-version result semantics and the already_separate outcome, which is useful but behavioral rather than parameter-level detail (e.g. the 10-item cap is left to the schema).

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+resource pair ('Move each version ... out of its asset into a new asset of its own') and fully specifies the outcome (same folder, named after the version, same sharing). It is clearly distinguishable from siblings like versions_add (its undo) and contents (which lists versions).

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?

Routes the agent explicitly: 'Undo it with versions_add' and 'contents(asset_id) lists an asset's versions' tell the agent when to reach for a sibling instead. The constraint that an asset always keeps at least one version and that already-alone versions return already_separate defines when the call is meaningful at all.

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