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

Annotations already declare non-read-only, non-destructive, non-open-world. The description adds valuable unsurfaced context: approximate coin costs per model, that reference photos are supported, the 7-input cap, and the async workflow (returns job_id, poll check_job). It does not state failure modes or whether images persist, but the added operational context is substantial.

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 default action, then layered decisions (model, resolution, aspect ratio, references, polling). Every sentence carries a decision the agent must make; no filler.

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?

With no output schema, the description supplies the return-value workflow (job_id then poll check_job), the default model/resolution, and the reference-image model constraints — enough for an agent to invoke and follow through correctly on a 6-parameter generation tool.

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 only 50%, so the description must compensate, and it does: it gives cost/quality tradeoffs for the model enum values, states the default resolution and why not to raise it, and explains the aspect_ratio enum values in plain terms (9:16 vertical, 16:9 horizontal, 1:1 square). It adds meaning beyond the raw enums, though a few enum values (google_nano_banana_edit, gpt4o_image, gpt_image_2) are never characterized.

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?

Opens with a specific verb+resource ('Generate an image') and immediately differentiates itself from the sibling generate_video by scope. The model-selection preamble makes the tool's role unambiguous 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?

Explicit when-to-use rules for each model (nano_banana_2 default, z_image only for cheapest, nano_banana_pro only for face preservation/max quality), a resolution rule (never 2K/4K unless asked), a mandated clarifying question for aspect ratio, and guidance on reference_image_urls for multi-character shots.

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