grade_clips

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

With no annotations, the description discloses batch behavior ('in one pass'), that values are read back, and that reports are per-clip so one failure does not hide the rest. This gives the agent insight into partial failure semantics. However, it doesn't state whether existing Lumetri effects are overwritten or whether the operation is reversible.

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?

Three sentences, each with a distinct function: mechanism, usage guidance, and failure reporting. 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?

For a 12-parameter mutation tool with no annotations and no output schema, the description leaves significant gaps: it doesn't explain parameter ranges, return value structure, or behavior with clips that already have a grade. It provides a good high-level model but isn't sufficient for full autonomous 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?

Schema description coverage is only 33%, and the description adds no parameter-level semantics. It references 'Lumetri Basic Correction' as a concept, but 8 numeric parameters are left undefined with no ranges or units, leaving the agent unable to reason about appropriate values.

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 states it applies a batch Lumetri Basic Correction to a group of clips in one pass, which distinguishes it from single-clip tools like set_lumetri and get_grade. The verb+object structure is specific and unambiguous.

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 explicitly recommends grading clips that share lighting conditions together and warns against a single correction across mixed lighting. This provides a clear when-to-use/not-use rule, even if alternatives aren't named.

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