Create color grade

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

The description goes far beyond the annotations by detailing the exact node chain created (Level, HSV Adjust, Movie File In, Lookup, Select, Ramp, Null), how the controls are exposed, and precisely what the return value includes (summary, JSON block with paths, exposed controls, errors, warnings, inline preview). It also explains the LUT loading mechanism and the standalone-build behavior, giving full visibility into side effects.

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 densely informative yet efficiently structured: it front-loads purpose, then explains mechanism, then input/output behavior, then alternatives. Every sentence contributes either a technical detail, a usage condition, or a critical distinction, with no redundancy or filler.

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?

Despite lacking an output schema, the description fully specifies what the tool returns, covering container path, node paths, exposed controls, errors, warnings, and preview image. The tool's complexity (10 optional params, branching behavior) is fully addressed through the chain explanation, mode behavior, and LUT loading details.

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 description coverage is 100%: every parameter already has a detailed description, including exact TOP parameter mappings (e.g., brightness1 not gain). The tool description adds only a high-level chain context (e.g., 'Level TOP applies lift/gamma/gain'), but this does not materially increase semantic understanding beyond the 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 vivid, specific verb-object pairing: 'Build a colour-grading / LUT finishing stage over a source,' and clarifies its niche as 'the make the final output look graded' tool for VJ sets. It also explicitly differentiates itself from the sibling tool apply_post_processing, removing ambiguity about its role.

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 clearly states when to choose this tool over an alternative: 'Use apply_post_processing instead to chain several distinct effects in series.' It also explains the two operational modes (with or without input_path), so the agent knows when to supply a source and when the tool will fall back to a test gradient.

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