color_grade

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

No annotations are provided, so the description carries the full burden, and it discloses nothing: not whether operations mutate the project, whether they are reversible, whether node graph or LUT changes persist, or what permissions are needed. For a mutation-oriented grading tool this is a total transparency 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?

It is short, but brevity here is under-specification rather than conciseness: the '[22 actions]' ellipsis replaces information the agent needs. The front-loaded 'Grading:' label is the one structurally sound element.

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?

A 22-action dispatcher with a freeform nested args object, no annotations, no output schema, and no enum is a high-complexity surface, and the description supplies only a keyword stub. It is far below what an agent needs to invoke the right action with the right arguments.

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 0% and 'action' is a bare string with no enum, so the partial action list in the description is the only hint at valid values – but it shows roughly 9 of 22 actions and never explains the nested 'args' object. The agent is left guessing both the action vocabulary and its payload shape.

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 colon-list identifies the domain (color grading) and enumerates sub-operations – primaries, curves, wheels, node graphs, LUTs, CDL, match grade, white balance, shared – which is enough to distinguish it from color_science and scopes siblings. However there is no explicit verb framing, and the enumeration is truncated to a generic '[22 actions]' placeholder, so the actual scope is only partially visible.

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 statement about when to use this tool rather than color_science, scopes, or effects, and no prerequisites or exclusions. The agent must infer that grading work belongs here purely from the word 'Grading'.

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