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

Annotations already flag destructiveHint and idempotentHint, yet the description adds substantial context beyond them: exactly what is destroyed (download URL, images, prompt.json, source kept for edit_image_set/export_icons), no credit refund, no undo, the API-key ownership constraint, partial-failure semantics, and zero cost.

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?

Dense and front-loaded with the destructive consequences, and every sentence carries distinct information. It runs long as a single block of clauses, which slightly hurts scannability.

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?

Covers destruction scope, irreversibility, auth requirement, batch limits, partial-failure behavior, and cost. With an output schema present, return-value detail is unnecessary, so nothing an agent needs to call this correctly is missing.

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, but the description adds real meaning: the batch limit ('Up to 50 ids per call'), the many-ids-per-set pattern, and the fact that not-found ids are reported without failing the call. The id-format explanation largely duplicates the schema description.

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?

Starts with a specific verb+resource+permanence qualifier ('Permanently delete one or more of your generations') and immediately scopes the timing ('before their download window closes'). Clearly distinguishable from delete_references and the generate_* siblings.

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 states the trigger condition ('Call it only when the user asks to delete generations'), names the automatic-deletion alternative that happens without it, and points to list_recent_generations and get_generations for obtaining ids.

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