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

With annotations (readOnlyHint=false, openWorldHint=true), the description adds value beyond them: it discloses the async nature, the need to poll get_generation, and the cost per swap. These operational details are not conveyed by the annotations alone.

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?

Two sentences with no waste: the first establishes purpose, the second packs in cost and async behavior. It is front-loaded and efficient.

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 generate-then-poll tool without an output schema, the description covers the essential workflow (async, polling, cost) and consent is captured in the required schema. It does not describe return payload details or error handling, but those are minor given the polling pattern. Overall, sufficient for correct invocation.

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%; each parameter already has clear descriptions. The tool description adds no additional parameter meaning beyond what the schema provides, so the baseline of 3 is appropriate.

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 states a specific verb+resource: 'Put yourself in any body and outfit' which clearly differentiates it from sibling tools like ai_head_swap or ai_outfit_changer. It also mentions cost and async behavior, giving a distinctive identity.

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?

Provides explicit workflow guidance: 'Runs asynchronously: returns a generation_id; call get_generation until status is "completed".' This tells the agent exactly how to invoke and poll, referencing the sibling get_generation. However, it does not explicitly compare with alternatives like ai_character_replace or ai_clothes_changer to help select among them.

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