Add Adjustment Layer

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false; the description usefully adds why it is non-destructive ('without touching their pixels', 'can be hidden or deleted later'). However it omits what the agent needs operationally: which layer must be selected first, whether extra parameters are ignored for the chosen type, and what identifies the new layer afterward.

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, front-loaded with the action and placement before the alternative-tool pointer. No filler, though the second sentence's sibling reference could have carried slightly more detail at the same length.

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 9-parameter tool with no output schema, the description never says what comes back (layer id/name) that the agent would need to later hide or delete the layer, nor that only the parameters matching 'type' take effect. It is adequate on intent and differentiation but leaves a practical gap on return value.

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 100%, so the type enum and every numeric range (hue, gamma, inputMin/inputMax, brightness, contrast, saturation, lightness) are already documented in the schema. The description adds no parameter meaning beyond that, which is the expected baseline when the schema does the work.

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 and resource ('Add a non-destructive adjustment layer above the active layer') and pins down placement and style. It explicitly separates itself from photopea_apply_adjustment, so an agent can choose between the two without reading 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?

Names one concrete alternative ('apply_adjustment') with the condition that selects it: non-destructive vs. pixel-altering. That is real routing guidance, but it does not cover other near-neighbours such as add_fill_layer, layer_mask, or set_layer_properties, and gives no explicit when-not-to-use caveats.

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