create_workflow

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

With no annotations, the description effectively communicates that the tool operates locally without contacting ComfyUI and has no side effects. It also warns that default params may reference models that must exist. This is solid behavioral context, though it could mention validation behavior of unknown keys (ignored) and any potential size limits.

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 two sentences that are well-structured and front-loaded. The first sentence clearly states the main function and templates. The second sentence adds important behavioral and usage context. Every sentence contributes meaningfully without redundancy.

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?

Given the complexity of generating workflow JSON, the description covers the essential aspects: what it does, side effect disclaimer, fallback behavior, and next steps. However, it lacks detail on the structure of the returned JSON (beyond 'complete workflow JSON') and does not mention output size or validation, leaving some gaps for an agent needing to handle the output.

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% with both parameters described. The description adds significant value by listing recognized keys for each template, explaining that unknown keys are ignored and omitted keys use defaults. This goes beyond the schema's minimal descriptions, helping the agent understand how to construct the params object.

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 it creates a ComfyUI API-format workflow from a built-in template, listing the six specific templates. It also explains the purpose of the generated workflow by referencing validate_workflow and enqueue_workflow, distinguishing it from sibling tools like enqueue_workflow itself.

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 explains that it's a pure local generation with no side effects and that unsupplied params fall back to defaults needing existing models. It suggests passing the result to validate_workflow or enqueue_workflow. However, it does not explicitly compare with other workflow creation methods like dsl_to_workflow or mermaid_to_workflow, leaving some ambiguity about when to choose this template-based approach.

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