Edit TouchDesigner node metadata

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

The description goes beyond annotations by detailing atomicity, prevalidation of fields, read-back verification, rollback on partial failures, safe parent moves (copy and validate before destroying source), and return format (final path and per-field results). This significantly enhances the agent's understanding of the tool's behavior, complementing the destructiveHint and openWorldHint annotations.

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 three concise, information-dense sentences. It front-loads the core purpose, then covers safety and return behavior, with no wasted words or repetition of schema details.

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?

For a complex tool with 14 parameters and no output schema, the description covers core functionality, atomicity, rollback, parent move safety, return values, and fallback behavior. It lacks some context around error conditions, valid flag combinations, or permission requirements, but is reasonably complete for the primary use case.

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?

With 50% schema description coverage, the description adds some context by grouping fields (e.g., 'exact Network Editor position' for node_x/node_y, 'parent moves' for parent_path, 'writable flags' for booleans). However, it does not elaborate on the meaning of undocumented flags like lock, bypass, render, viewer, display, cloneImmune, or allowCooking, leaving gaps for the agent to infer.

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 identifies the tool as an atomic editor for an operator's name, parent, position, color, comment, and writable flags, using specific verbs and resources. It distinguishes itself from sibling tools like update_td_node_parameters by focusing on metadata rather than parameter values, and from create/delete tools by explicitly stating it edits.

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 clear context for when to use the tool—when editing metadata fields atomically—and mentions behavior such as prevalidation and rollback. However, it does not explicitly name alternative tools like update_td_node_parameters or delete_td_node for exclusion, leaving some inference to the agent. The mention of 'Does not use raw Python fallback' implicitly steers away from execute_python_script.

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