comfy_publish_subgraph

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

The annotations already provide readOnly=false, idempotent=true, and destructive=false, so the core behavioral profile is covered. The description adds a useful validation constraint on the name parameter (must not contain '/' or '..') and clarifies that this is a local save-and-reuse operation, but it does not explain whether an existing blueprint is overwritten, where the blueprint is stored, or any side effects beyond saving.

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 tightly formatted: one summary sentence followed by a clear Args block with short, purposeful explanations. Every sentence has architectural value, no unnecessary detail or repetition. It is easy to scan and understand.

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 tool's four parameters and the nested object type for nodes, the description covers all input parameters and provides essential context. An output schema is present, so the description does not need to document return values. The missing details about node_spec are a small downside, but overall the tool is fully usable from the description alone.

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 description coverage is 0%, so the description carries the entire burden for parameter semantics. Each of the four parameters gets at least one meaningful detail: name has a restriction, nodes is described as a dict of node_id: node_spec, description is for discoverability, and tags are for search/filter. The main gap is that 'node_spec' is left undefined, but the description still adds substantial value beyond the bare schema.

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 opens with a specific action: "Save a set of nodes as a reusable blueprint." This clearly explains what the tool does and conveys the intended result, especially recognizing that publishing a subgraph creates a reusable blueprint. However, it does not explicitly differentiate the tool from sibling tools like comfy_insert_blueprint or comfy_save_technique, so it stops just short of the strongest purpose clarity.

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 no guidance on when to use this tool versus alternatives such as comfy_save_technique, comfy_export_workflow, or comfy_insert_blueprint. It states the action but gives no context regarding which scenarios call for creating a reusable blueprint, and it mentions no exclusions or alternative tool recommendations.

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