delete_actor

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states that the actor is deleted, but does not warn that the operation is irreversible, clarify whether the name must be exact or unique, or describe what happens when no actor matches. The KB pointer may contain such details, but the description itself does not reveal them.

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 concise and front-loaded with the action and target, followed by a useful example and KB reference. There is no fluff, and the brevity is appropriate for a tool with a single parameter.

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 destructive mutation with no annotations and a single fully undocumented parameter, the description is under-specified. It does not warn about irreversibility, suggest how to discover a valid actor name, or describe failure behavior. The happy path is covered, but an agent cannot anticipate common misuse cases.

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?

The only parameter, name, is given meaning by the phrase 'by name' and by the concrete example delete_actor(name="ExampleName"). Since schema description coverage is 0%, this partial compensation is useful, but the description still does not specify exact-match behavior, case sensitivity, or whether duplicate names are handled.

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 exactly what the tool does: 'Delete an actor from the level by name.' The verb is specific and the resource target is clear, and the example demonstrates the intended invocation. It does not explicitly differentiate from sibling tools like find_actors_by_name or delete_blueprint_node, but the delete-by-name semantics are unambiguous enough on their own.

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?

There is no guidance on when to use this tool versus alternatives, no prerequisites such as first finding a valid actor name, and no caveats about child actors, references, or irreversible consequences. The KB pointer and example help with invocation, but not with selection between this and related actor tools.

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