saturation

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

Annotations already declare destructiveHint=true, and the description adds useful behavioral context by stating 'Non-linear stage' and emphasizing 'Checkpoints first', which signals that the operation mutates pixel data and should be preceded by a checkpoint. It does not contradict the annotations.

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?

The description is extremely compact—two short sentences with no filler. It front-loads the core purpose and each remaining clause ('Non-linear stage', 'Checkpoints first') adds distinct operational 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?

The description gives enough to start using the tool cautiously, especially with the checkpoint warning and mode hints. But it omits the meaning of the required id parameter, does not explain curve pair semantics, and offers no routing to alternatives, which leaves meaningful gaps for a four-parameter destructive tool.

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?

With schema description coverage at only 25%, the description does useful work by defining amount's range and default (-1..1, 0.3) and characterizing curve as a hue curve. However, it leaves the required id parameter undocumented and does not clarify how amount and curve interact when both are provided.

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 identifies the operation as a color saturation boost with two modes (amount or explicit hue curve), so an agent can infer what the tool does. However, it uses a noun phrase rather than a specific verb like 'apply' or 'adjust', and it does not explicitly distinguish itself from sibling tools such as curves or color_calibrate.

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 phrase 'Non-linear stage' gives clear workflow context for when the tool is appropriate, and 'Checkpoints first' states a prerequisite. It does not name alternatives or list exclusions, but the usage context is explicit enough to guide selection.

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