delete-layer

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

This is a destructive operation with no annotations to signal the risk. The description merely says 'Delete' and mentions targeting, but it does not disclose that deletion is irreversible, what happens if both layerName and layerIndex are provided, or what errors occur if no target is specified. The description carries the full burden of behavioral disclosure and fails to address these important safety and edge-case behaviors.

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 two sentences, front-loaded with the core action ('Delete a layer from a composition'), followed by the key targeting detail. No filler or redundant content; every word serves the purpose.

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 tool has no output schema and no annotations, and the description does not explain essential operational details. It fails to specify that exactly one of layerIndex or layerName is required (since the schema marks all parameters as optional), or what happens if both or neither are provided. It also does not describe error behavior for missing compositions or layers. Given the simplicity of the tool, these gaps make the description incomplete for reliable agent use.

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 coverage is 100%, so all parameters are described in the input schema. The description adds 'Target the layer by layerIndex or layerName,' which reiterates the schema's own parameter descriptions but does not add deeper meaning such as mutual exclusivity, precedence, or required-target logic. It provides marginal value beyond the schema, so baseline 3 is appropriate.

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 states a specific action ('Delete a layer from a composition') with a clear resource (a layer) and context (composition). It distinguishes from sibling tools like duplicate-layer and inspect-layer by naming a unique operation. It also specifies targeting via layerIndex or layerName, making the purpose unambiguous.

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 by the verb 'Delete' and the resource type. However, there is no explicit guidance on when to use this tool vs alternatives, no mention of exclusions (e.g., cannot delete locked layers), and no note about requiring a composition to be active. The description provides clear context but no explicit when-to-use or when-not-to-use guidance.

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