create_node

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals that the tool can create any node type, implying significant flexibility and potential side effects (dependencies on parent path, etc.), but it doesn't explicitly state whether this is destructive or requires specific permissions. It doesn't discuss error cases (e.g., if node_type is invalid) or confirm whether the node is created immediately or requires cooking. Given the lack of annotations, this is a moderate gap, not severe.

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 well-structured: it starts with a clear one-sentence purpose, then provides a context paragraph explaining the importance of checking dedicated nodes, and ends with a parameter list. It is concise with no wasted words; every sentence earns its place, though the parameter list could be a little more compact. Overall, it's efficient and front-loaded with the key guidance.

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 is a creation operation with moderate complexity (4 parameters, no enums, no output schema). The description covers the purpose, usage guidance, and parameter semantics, which is sufficient for an agent to call it correctly. It doesn't discuss error handling or return values, but those are not critical given the lack of output schema. The guidance to check list_node_types adds important context that ensures correct usage. This is nearly complete, missing only edge-case behavior.

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 0%, so the description must compensate. It does, by listing each parameter with a brief explanation: 'parent_path: Parent network path', 'node_type: Node type (e.g. 'geo', 'box', 'grid')', 'name: Node name', 'position: [x, y] network editor position'. This adds meaning beyond what the schema provides (which only has type and default), giving the agent concrete information on how to use each parameter. The examples for node_type are particularly helpful.

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 creates a node inside a parent network, with a specific verb ('Create') and resource ('node'). It also distinguishes itself by referencing the need to check for dedicated node types, which is unique and differentiates it from siblings like create_wrangle or create_vex_expression. The purpose is unambiguous and easy to understand.

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 gives explicit usage guidance: it instructs the agent to call list_node_types first to verify a dedicated node exists, and explains that Houdini has thousands of nodes with many common operations having dedicated nodes that are better than writing VEX/Python. This explicitly tells when to use this tool and when to prefer alternatives, which is well above average.

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