set_clip_grade

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

With zero annotations, the description carries the full burden, but it only restates the operation without disclosing side effects: whether grading replaces or stacks on an existing grade, whether reset clears other parameters, or whether this is destructive/reversible. The presence of a reset parameter hints at behavior, but the description never explains it. Mutations with no behavioral context are a significant gap.

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 tight sentences: the first delivers verb + resource + parameter mapping, the second adds a practical usage tip. No filler, no repetition of schema defaults, and the key scoping information is front-loaded.

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?

The output schema covers return values, and the description handles the CDL parameters well. But for a 7-parameter mutation tool, the unexplained reset and node_index semantics, plus the ambiguity about whether the grade overwrites prior grading, leave noticeable gaps an agent must guess about before invoking.

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%, so the description must compensate, and it does add real value by mapping the CDL aliases (slope/gain, offset/lift, power/gamma) to parameters and explaining the saturation=0.0 black & white trick. However, two parameters—reset and node_index—are left entirely unexplained, and the '1.0 1.0 1.0' triple-string format is not described, so compensation is only partial.

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 uses a specific verb ('Apply') on a clear resource ('clip') and names the exact grading domain (ASC-CDL with saturation, slope/gain, offset/lift, power/gamma). It is clearly distinct from siblings like get_clip_grade (getter) and keyframe_clip_saturation (animation), though it does not explicitly name or exclude any sibling.

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?

No guidance is given about when to use this tool versus alternatives such as set_clip_color, animate_color_fx, or get_clip_grade. The 'saturation=0.0 for black & white' tip is a usage nuance, not a routing rule. An agent must infer the tool's place among 40+ siblings from the name alone.

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