build_scene_adjustment_layers

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

With no annotations, the description carries the full burden and does disclose real behavioral traits: layers are created on an adjustment track, each receives a Lumetri with a base look and optionally the source clip's grade, and layers are named after their source. It also implies (via 'clip grade transferred') that source clips are altered. What's missing is preconditions, error behavior, and the fact that existing items on the adjustment track are replaced — that destructive detail lives only in the schema.

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?

Two to three sentences, front-loaded with the core action and grouping rule, with no filler. The parenthetical "(optionally)" is the only mildly ambiguous fragment; otherwise every clause carries information about what is built and how.

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 9-parameter mutating tool with no annotations and no output schema, the description explains what gets created and how layers are grouped, but omits prerequisites, return information (e.g., created layer names/count), and failure modes. Adequate to call correctly, incomplete for predicting side effects on the timeline.

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%, so every parameter (look, namePrefix, sourceTrack, adjustmentTrack, skipPrefixes, transferClipGrade, adjustmentItemName) is already documented in the schema, setting the baseline at 3. The description adds relation-level meaning — that look is applied on top of the transferred grade, and that naming derives from the source — but does not explain the skipPrefixes or track-default interplay beyond what the schema states.

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?

States a specific verb and resource ("Creates one adjustment layer per scene above the source track") plus the grouping rule that defines a scene (same source/camera shares a layer, different source gets its own). This is far more precise than a generic 'add adjustment layer'. It stops short of naming the near-identical siblings (add_adjustment_layer, add_scene_color_layers), so an agent must infer the differentiation.

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?

Usage is implied by the described outcome: batch-creating per-scene gradeable layers above a source track. There is no explicit when-to-use/when-not, no statement of prerequisites (sequence open, clips present on sourceTrack), and no routing away from add_adjustment_layer or add_scene_color_layers, which appear to be the obvious alternatives.

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