generate_image

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

Annotations only flag non-readonly, open-world, non-idempotent. The description adds the critical behavior annotations don't cover: every call consumes quota/credits, variations cost separately, a 402 means over-limit with no retry, and the message should be surfaced verbatim. That is exactly the context an agent needs before a paid, non-idempotent call.

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 purpose, job flow, and cost warning before the bulleted aspect-ratio reference, so the important parts are not buried. The platform bullet list is somewhat long but each line maps a real decision to a concrete ratio, so it earns its place.

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 12-parameter, asynchronous, credit-consuming generation tool with no output schema, the description covers the full lifecycle (queue, poll, hand off), the cost/confirmation gate, and the over-limit failure mode. Nothing an agent needs to invoke it safely 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% and the field descriptions are already detailed (credit tiers per model/resolution, thinking_level precedence over quality, xAI constraints). The description still adds value by supplying the platform-to-aspect-ratio mapping that the aspect_ratio field explicitly defers to ('see tool 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?

States a specific verb and resource ('Queue an AI image job') plus the underlying providers (Nano Banana/Gemini, Grok Imagine/xAI), and immediately declares the return value (job_id). This clearly separates it from the nearby generate_video and upload_media 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?

Gives an explicit end-to-end workflow: call this, poll list_jobs with type=image, then feed urls into create_post as media_url/media_urls. It also names a when-not-to-call rule ('Do NOT call speculatively') and the confirmation prerequisite.

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