save_look

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

With no annotations, the description carries the burden and it does disclose the key behavioral trait: the effects are harvested from the adjustment clip in the currently open timeline, and ref falls back to the sole adjustment clip. It leaves out what happens on a name collision, whether a look is overwritten, and what the tool returns, which matters for a persistence operation.

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?

Front-loaded with the action and result, and the trailing sentence about ref's default is genuinely useful. The aside 'e.g. the one you made with your colour preset' and the informal 'no more Option-A by hand' add color but little precision.

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?

No output schema and no annotations, yet the description covers purpose, source, and the apply_look pairing. It is still incomplete for a three-parameter mutation: make_default is undefined, overwrite/error behavior is unstated, and nothing indicates what the agent gets back after saving.

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 all three parameters need the description. It clarifies ref's meaning beyond the bare null default ('the only adjustment clip') and implies name is the look's label, but make_default is never mentioned despite defaulting to true — an agent cannot tell what it changes.

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?

Specific verb (save) plus resource (effects on an adjustment clip) plus the resulting artifact (a reusable look), with the source clip scoped to the open timeline. It also implicitly separates itself from apply_look, which consumes what this tool produces, so an agent can place it in the workflow without opening either schema.

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 states the condition for use (you have graded an adjustment clip and want that treatment reusable in future rough cuts) and names apply_look as the companion consumer, which is real routing guidance. It stops short of explicit exclusions — e.g. whether copying effects directly with copy_effects is the alternative when you don't want a persisted look.

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