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

Annotations only declare non-read-only, open-world, non-destructive. The description adds the material facts annotations cannot carry: every call and every image is billed, results are already rendered inline, and the call returns an asset_id for later edits. The cost and idempotency disclosures are precisely the risk-relevant behavior an agent needs before invoking a paid generation 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-loaded with the core capability, then the constraints in descending order of importance (billing, single-call rule, batching, return value). Every sentence carries an operational instruction; nothing is decorative or repeated.

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 7-parameter generative tool with no output schema, the description covers the missing pieces an agent needs: cost model, retry/suppression behavior, the inline rendering that replaces a show_images call, batch-via-count, and the asset_id returned for follow-up edits. Nothing essential to correct invocation is absent.

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%, so the schema already documents all seven parameters well and baseline is 3. The description still adds value by stating count goes 'up to 4' in one call and by explaining the asset_id return that feeds reference_asset_ids, but it does not add anything about resolution, aspect_ratio, or reference limits beyond what the schema says.

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 concrete verb+resource pair and covers both modes ('Generate an image from a prompt, or edit/combine images by passing them as references'), which maps directly onto the reference_urls/reference_asset_ids parameters. It also names sibling tools (show_images, list_models) so an agent can separate this from adjacent capabilities without opening the 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?

Gives explicit when-to-call and when-NOT-to-call guidance: call once per request, do not retry/refine/verify, do not follow with show_images, and only re-call if the user asks for changes. It also routes multi-option requests to the count parameter instead of repeated calls, which is exactly the ambiguity an agent would otherwise guess wrong on.

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