Search TouchDesigner code

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

It discloses read-only behavior, bounded search, redacted output, completeness metadata, and exclusion of fallback to raw Python/whole DAT exports. This complements the readOnlyHint and openWorldHint annotations with actionable constraints.

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 dense sentences that front-load the core behavior and add critical constraints without redundancy. Every phrase earns its place.

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 output schema and annotations, the description supplies necessary context: scope (live project), behavior (read-only, bounded), result shape (redacted excerpts with provenance), and environmental constraints (works with exec disabled). This is sufficient for an agent to decide invocation.

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 description clarifies that query is a lexical search string and source_kinds covers DAT text/parameter expressions, but it does not explain the numerous limit/scan parameters or filters like family and type_match. Schema descriptions cover about half the parameters, so the description only partially compensates.

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 specifies a unique action: bounded BM25-style lexical search across DAT text and parameter expressions, with result characteristics (redacted excerpts and provenance). It clearly distinguishes from sibling tools like execute_python_script or search_operators by stating it never falls back to raw Python or exports whole DATs.

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?

It explicitly notes the tool works even when TDMCP_BRIDGE_ALLOW_EXEC=0, giving a concrete usage scenario. However, it does not name alternative tools or say when not to use it, relying on the scope to imply appropriate usage.

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