Look up TouchDesigner script module help by name, choosing full, summary, or minimal detail and YAML or JSON output.
help() output for a td name.
name (<class 'str'>): Name to look up.
detail (str | None): full (default) | summary (long lists cut to 25 + count) | minimal (top-level scalars only).
response_format (str | None): yaml (default, token-cheap) | json.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| detail | No | ||
| response_format | No |
Changes observed during successful MCP inspections.
v0.4.0Input schema / properties / detailAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Detail"
+}Input schema / properties / response_formatAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Response Format"
+}v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden and it does reveal important behavior: 'full (default) | summary (long lists cut to 25 + count) | minimal (top-level scalars only)' and 'yaml (default, token-cheap) | json'. It does not explicitly state side-effect/read-only status, but the informational nature of help() makes that gap minor.
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 compact and front-loaded, with no filler text; every line contributes parameter or default information. It loses a point for being a bare, somewhat cryptic phrase ('for a td name') rather than a structured one-sentence overview plus clean parameter list.
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 three-parameter informational tool with no output schema, the description covers the call shape and output modes, but it omits what 'td' means, example values, error behavior, and any relation to the sibling class/script detail tools. It is minimally viable but relies on the reader's domain knowledge.
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%, and the description compensates by documenting every parameter with allowed values and defaults, e.g., detail's three modes and response_format's yaml/json choice. The name parameter is only 'Name to look up', which is minimal but adequate for a help lookup.
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 opening line 'help() output for a td name.' identifies the action (return help output) and the resource (a named td object), so it is not a tautology. It is reasonably clear but assumes the reader knows what a 'td name' is and does not differentiate this help tool from nearby script_class_list/script_class_detail siblings.
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?
There is no guidance on when to choose this tool over alternatives such as script_class_list or script_class_detail, and no statement of exclusions or prerequisites. The detail/response_format options describe how to call it, not when to call it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.