create_workflow

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

With no annotations, the description carries the full burden, and it excels. It explicitly states side-effect-free behavior for `create` ('does not contact ComfyUI and has no side effects'), that `validate` does not execute, that `node_info` requires a reachable ComfyUI instance, and even discloses the staleness caveat with `refresh`. It also warns that `create` may reference models that must exist on the server. This is transparent and comprehensive.

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 long but highly structured and information-dense. It begins with a one-line purpose statement, then uses bullet points for each action, making it easy to scan. Every sentence adds value, such as listing template names, operation types, and clear return-value expectations. There is no redundancy or filler; it is appropriately sized for the tool's complexity.

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 description fully covers all four actions, their parameters, and return values. It explains that `create` returns the complete workflow JSON, `modify` returns modified JSON plus new node IDs, `validate` returns errors/warnings, and `node_info` returns structural or verbose definitions. It also notes the acceptable input formats for `validate` (API or saved UI export). Given no output schema, this is complete guidance for an agent to call the tool correctly.

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?

While the schema covers 100% of parameters with detailed descriptions, the description adds meaningful behavioral context beyond the schema. For example, it explains that unsupplied `params` fall back to template defaults and that the result may reference models that must exist on the ComfyUI server. For `node_info` it describes the structural summary vs. verbose output and the 20-node threshold. These extras go beyond the schema's property descriptions, justifying a score above the baseline of 3.

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 tool's purpose: 'Author and check ComfyUI workflow JSON.' It then breaks down each action (`create`, `modify`, `validate`, `node_info`) with specific verbs and resources, making it obvious what each operation does. It also distinguishes itself from siblings by noting that `create` is 'pure local generation' with no ComfyUI contact, which differentiates it from `enqueue_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?

The description provides explicit routing guidance: it tells the agent to pass the output of `create` to `validate` or `enqueue_workflow`, explaining that `validate` runs without executing, and `node_info` is for inspecting installed node types. It also clarifies when to use `refresh` and `verbose`, giving clear contextual triggers. This is strong usage guidance with direct references to alternative tools.

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