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

Annotations already flag destructive/idempotent/not-readOnly, but the description adds substantial context: what is destroyed (download URL, images, prompt.json, full-resolution source for edit_set/export_set), that it cannot be undone, that credits are not refunded, the API-key ownership requirement, the 50-id cap, the not-found-ids-do-not-fail semantics, and that it costs no credits.

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-loaded with the action and its permanence, then details; every clause carries new information. It is a single dense run-on paragraph, which makes it harder to scan than a segmented form, but there is little wasted text.

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 destructive one-parameter tool with an output schema already describing returns, the description covers everything an agent needs: irreversible effects, auth scoping, batching limits, partial-failure behavior, and cost.

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% so the baseline is 3, and the description goes beyond it by defining the id format ('the random segment of each one's download URL'), explaining the multi-call set case, and stating the 50-ids-per-call limit that the schema does not encode.

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 and resource ('Permanently delete one or more of your generations') plus the scope constraint (before the download window closes). It is clearly distinguishable from delete_references and from the automatic expiry mentioned later.

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?

Explicitly says when to call it ('only when the user asks to delete generations') and supplies the implicit alternative — if you do nothing, generations are removed automatically when the download window closes. It also names list_recent_generations and get_generations as the way to obtain the ids.

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