update_layer

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

With no annotations, the description carries the full disclosure burden, and it does add real behavioral detail: 'layer' defaults to the active layer, opacity is 0..1, blend_mode takes Krita ids, and x/y set absolute bounds while dx/dy are relative. However, it never says what happens when no properties are supplied, whether partially supplied fields are left untouched, or what the 'name' parameter actually does (rename vs. selector), which is a genuine ambiguity given 'layer = id or name'.

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 a one-line purpose followed by a compact per-parameter glossary; no filler and no repetition of the schema types. It could be marginally better structured by separating the target-selection parameters from the properties being changed.

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 14-parameter mutation tool with no annotations, no output schema, and no schema descriptions, the definition covers the majority of the surface but is not complete: four parameters are undocumented, partial-update/no-op semantics are unstated, and there is no hint about failure modes such as an unknown layer or invalid blend mode id.

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% across 14 parameters, so the description has to compensate; it explains 10 of them with useful detail (opacity range, blend_mode id list, alpha_locked, inherit-alpha clipping, color_label 0-8, absolute vs relative positioning). It leaves 'name', 'locked', 'visible', and 'activate' (default false) completely unexplained, and the 'name' omission is the most costly since it is easily confused with the layer-name selector.

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?

"Change layer properties" states a specific verb and resource, and the parameter glossary makes the scope concrete (opacity, blend mode, alpha lock, clipping, bounds). It does not explicitly distinguish itself from siblings like transform_layer or arrange_layer, which also touch layer geometry/stacking, so an agent must infer the boundary.

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?

Usage is implied rather than stated: the parameter list suggests it is the general-purpose mutator for an existing layer, as opposed to create_layer/delete_layer/duplicate_layer. There is no explicit when-to-use or when-not-to-use statement, and no mention of how this relates to transform_layer for the x/y/dx/dy case.

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