create_instance

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

No annotations are provided, so the description carries the full behavioral burden, yet for a mutating tool it says nothing about required permissions, error behavior on an invalid className or property, whether the creation is undoable, or what happens when a non-BasePart class receives an unsupported property. The only behavioral hint is the value-encoding convention, which is more parameter than behavior.

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?

Two sentences, zero filler, with the core action and examples front-loaded and the value-encoding rule appended as a second, self-contained clause. Every element earns its place.

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?

With no annotations, no output schema, and a nested free-form properties object, the description covers the creation call adequately but omits what the call returns (instance path/reference) despite sibling tools like get_instance, set_property and delete_instance operating on paths. An agent cannot tell from the description how to address the instance it just created.

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 only 50% (name and properties are undocumented), and the description fills the most important gap: the opaque 'properties' object accepts Roblox typed values via {__type:'Vector3'|'Color3'|'UDim2'|'CFrame'|'BrickColor', value:...} or plain JSON. That encoding rule is essential and unavailable in the schema, though it does not cover the 'name' parameter or default naming.

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 (Create) and resource (any Instance) and enumerates concrete class examples (Part, Model, Folder, PointLight, SelectionBox), which distinguishes it from specialized siblings like create_script and create_gui. No sibling is named as an alternative, so it stops short of full differentiation.

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 'Create any Instance' with optional parent/name/properties, but there is no explicit guidance on when to prefer this over create_script, create_gui, or bulk_create for multiple instances. The agent must infer routing from the sibling names alone.

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