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

Beyond the annotations (readOnly=false, idempotent, non-destructive) it discloses that edits are saved as an undoable version (undo_edit), cost no Horizon Units, and that reset=true neutralizes light and color before applying values. It also explains the async return path via job_id. It does not describe what happens to unspecified parameters on a repeat call, which is the main remaining behavioral 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?

Front-loaded with the user-intent triggers, then ranges, then recipe examples, then exclusions and the job flow — a sensible ordering for a 26-parameter tool. It is dense and runs together (the guide examples read as a compressed run-on), but essentially every clause carries distinct information.

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 26-parameter mutation tool with an output schema and a 0%-covered input schema, the description supplies ranges, sibling exclusions, undo behavior, cost, and the job_id polling path — everything an agent needs to invoke it correctly. Return-value details are legitimately left to the output schema.

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% (titles only), so the description carries the full burden and does: numeric ranges and units for nearly every knob (exposure -2 to 2 stops, contrast 0.5-1.5, saturation 0-2 with 1 = as is and 0 = black and white, highlights/shadows/etc -1 to 1, hue -180 to 180, sharpen/vignette/grain/fade 0-1), the color band vocabulary, and the meaning of start_seconds/end_seconds and reset.

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+resource (change light and color of a clip or photo) and anchors it with concrete user phrasings like "brighten this photo" and "make the sky bluer". It explicitly excludes the adjacent siblings style_clip (filter looks/effects) and frame_clip (crop/zoom), so the boundary is 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?

Opens with an explicit when-to-use trigger list, then names the two alternatives and what they cover instead. It also gives a post-call workflow (poll job_status, then preview_frame) and explains that a follow-up "a bit more" should build on the values reported in the notes rather than restarting.

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