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

Adds substantial context beyond the annotations: the call is asynchronous and returns a job id, the result is only a preview, nothing enters the operator's frame list until save_frame, and each generation consumes the account's free daily allowance. This goes well beyond the readOnly/destructive hints already provided.

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 dense but every sentence carries operational value—purpose, asynchronous behavior, persistence path, refinement path, and cost warning. It is front-loaded with the tool's core purpose and then layers critical caveats in a logical order.

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 complex async generation tool, this description covers the full lifecycle: initiation, result checking, refinement, persistence, and cost implications. The output schema covers return details, so nothing needed to call and handle this tool correctly 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?

Although schema coverage is 100%, the description enriches the parameters: it clarifies that prompt should be in the operator's own words and not include brands, explains layout meanings including the 'strip-3' default expectation, and notes that the Studio picks the closest shape when a layout doesn't support the requested one.

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: 'Start designing a new photo frame' from a description of the desired look, and clarifies it 'opens a design thread and makes the FIRST version.' It clearly differentiates itself from sibling tools like check_generation, refine_frame, and save_frame by naming each one's role in the workflow.

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 routing: call check_generation to see the result, call refine_frame with the threadId to change a result rather than starting again, and call save_frame to persist. It also gives negative guidance—do not call speculatively, twice for the same request, or while another generation is running.

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