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

With no annotations provided, the description carries the full behavioral burden, and it does so thoroughly. It discloses that the call starts an async job, returns id and credits_charged immediately, requires polling or a wait helper, and that completed projects include download URLs. It also warns about hotlinked URL failure and recommends the presigned upload flow, which is valuable behavioral context beyond what the schema provides.

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?

The description is front-loaded with the core purpose, then uses two clearly labeled bullet sections for async behavior and file-path guidance. Every sentence adds value, and there is no redundant restating of schema fields. The structure makes the most important operational details easy to scan.

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 tool with nested assets, an enum parameter, and async behavior, the description is complete. It covers immediate return values, completion statuses, how to retrieve finished images, and how to handle input files correctly. Given the output schema exists, the lack of additional return-value detail is not a gap.

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 a baseline of 3 applies, but the description adds meaningful context beyond the schema. It explains that resolution drives credit cost and gives explicit file-handling guidance for *_file_path values, including when direct URLs may or may not work. This extra guidance helps an agent avoid common invocation errors.

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?

The description opens with a specific verb and resource: 'Swap a person into a scene image using Nano Banana 2 Lite or Nano Banana 2.' It clearly identifies the tool's core function and scope, making it easy to distinguish from sibling create-image tools like face_swap_photo_create_image or head_swap_create_image. The model and resolution details further clarify what makes this tool unique.

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?

The description gives clear, actionable guidance: it explains the async nature, tells the caller to use wait_for_image_project with the returned id, and recommends preferring Magic Hour file_path values over direct URLs. It does not explicitly name sibling tools as alternatives or state when not to use this tool, but the context is strong enough for an agent to select it appropriately.

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