create_layer

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

With no annotations, the description carries the full burden and does well: it discloses the side effect that the new layer becomes active, that fill/filter layers are non-destructive, that clonelayers and filelayers stay live-linked, that masks attach to parent (defaulting to the active layer), and that creation is clipped to the current selection. It omits failure conditions (no open document, invalid filter name) and whether the operation is undoable.

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 core purpose is front-loaded and the length is defensible given 12 undocumented parameters, but the body is a dense run-on enumeration with dangling fragments ('type:', 'parent = ...; above = sibling to stack over.'). Bullet-per-type formatting would preserve the same content with far better scanability.

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 12-parameter creation tool with no annotations and no output schema, the description covers nearly everything an agent needs to construct a valid call, including nested config shapes. The remaining gap is return behavior — it never says what comes back (e.g. the new layer's id/name), which matters since no output schema exists.

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 12 parameters, so the description must compensate and largely does: fill, path, parent, above, filter, filter_params, source, pattern, generator, generator_config, and type each get concrete meaning, including worked generator_config examples for seexpr, screentone, and gradient. Only 'name' (default 'Layer') is left to obvious inference.

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 up front ('Create a layer or mask') and then enumerates every creatable type (paintlayer, vectorlayer, grouplayer, filllayer, filterlayer, clonelayer, filelayer, filtermask, transparencymask). This makes it unmistakable versus siblings like update_layer, duplicate_layer, or delete_layer, and the 'becomes the active layer' clause fixes the resulting state.

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?

Guidance is embedded per type: filllayer for non-destructive colour/pattern, filterlayer for non-destructive adjustment of everything below, clonelayer for live mirroring, filelayer for a live-linked image, plus the selection caveat and the parent default of 'active layer'. It never names a sibling to use instead (e.g. update_layer for modifying an existing layer), so the when-not path is left implicit.

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