decompose_layers

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

With no annotations, the description must disclose behavior but only states it returns a task id, status, and output URLs. It does not reveal that the operation is likely asynchronous, that status may require polling, that image_url has format/size constraints, or any error/rate-limit behaviors. Key behavioral aspects are omitted.

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 concise and well-structured in a single sentence, avoiding verbosity. However, it is too sparse to cover essential context, but for what it says, it is clean and understandable.

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?

The tool has no annotations, and the description only provides a high-level summary. It omits important context such as asynchronous behavior, input constraints beyond that in the schema, output details, and relationship to other tools. Significant gaps remain for an agent to reliably use the 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?

The schema provides descriptions for 5 of 9 parameters (56% coverage), including essential ones like image_url, wait, model, prompt, and output_format. However, the description itself adds no parameter-level detailahan selain that it returns a task id, status, and output URLs. Parameters like size, timeout_ms, callback_url, and poll_interval_ms are left undocumented in both schema and description, leaving gaps.

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 clearly states the action (creating a Seedream task) and the resource (RunAPI for decompose layers), but does not elaborate on what decomposition entails or distinguish it deeply from sibling image editing tools. It is more specific than a tautology but lacks detailed purpose context.

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?

No guidance on when to use this tool vs. alternatives like edit_image or get_task. The description only says 'Create a Seedream task' without mentioning prerequisites, use cases, or exclusions. The schema hints at asynchronous behavior via wait/poll parameters, but the description itself offers no usage direction.

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