delete_layer

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

With no annotations at all, the description carries the full behavioral burden and mostly fails it. It does not state that deletion is destructive or whether it is undoable via the undo sibling, what happens to pixels in the removed layer, or what occurs if the named layer does not exist. Only "Returns status dict" hints at the outcome, and even that is vaguer than an output schema would be.

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 one-line purpose is front-loaded, followed by a tight parameter list that adds information rather than echoing the schema. Every sentence earns its place and there is no filler.

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 zero-annotation mutation with no output schema, an agent still lacks the safety picture: reversibility, failure modes, and side effects on the image state are unaddressed. The address-mode logic and defaults are complete, so the definition is usable but not sufficient on its own.

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%, so the description must compensate, and it largely does: all three parameters are explained, the mutual exclusivity of layer_name and layer_index is made explicit, and both defaults (image_index=0, fall back to active layer) are stated. Gaps remain on whether layer_index is 0-based and whether layer_name must be unique.

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?

"Delete a layer from an image" states a specific verb and resource, and the target (a layer within an image) is unambiguous. It separates cleanly from sibling layer tools like create_layer, duplicate_layer, rename_layer, and reorder_layer purely by verb, though it never names them.

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 description gives within-call selection guidance ("Provide either layer_name or layer_index. Defaults to active layer if neither given"), which is genuinely useful for choosing an address mode. It gives no broader when-to-use context: nothing about preferring flatten_image or merge_visible_layers, nothing about prerequisites, and no warning that this is a destructive operation.

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