Create instances

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

Annotations state this is a destructive mutation (readOnlyHint: false, destructiveHint: true), and the description aligns with that. Since annotations carry the primary burden here, the description adds value by clarifying the behavior at creation time: the 'undoable step' framing, atomicity with children, and the important caveat that paths are unknowable until the instance exists. The note about API validation against the live Roblox dump is a genuine behavioral insight beyond what annotations provide. Not a perfect 5 because the validation behavior could have mentioned what the sibling tool does for scripts (it does, via script_create).

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 dense but not bloated; it front-loads the core action, then explains the nested optimization, then gives the validation warning, then the sibling pointer. The only redundancy is that 'as one undoable step' appears in both the first sentence and the second paragraph, adding negligible value the second time.

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 (but not irreversible in the Studio sense, since it's a single undo step) mutation tool, the description and annotations together tell an agent what it mutates, why it's safe to use in a loop (atomic), and how to avoid common error states (path guessing). The `parent` field being required only at top level is in the schema, but the description could have been more explicit about how nested children interact with the parent's absent `parent` field.

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 has 100% coverage, so the description doesn't need to re-document parameters. It goes beyond the schema by explaining the rationale behind the `children` parameter (avoid path guessing) and hinting that property values follow Studio's display format ('12, 0, 5' for Vector3). A full point taken off only because it doesn't detail all possible property formats—it gives examples instead of an exhaustive list.

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 clearly states the tool creates instances with properties, attributes, and tags as one atomic undoable step. It mentions real behavior (schema validation, nested creation) that distinguishes it from generic creation tools. It loses a point because naming the sibling 'script_create' as the alternative for scripts is more thoroughly covered under 'Usage Guidelines', and the verbose initial sentence buries the core purpose slightly.

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?

Explicitly names the alternative tool for script creation (script_create) and the exact condition for choosing it. The description also gives best-practice guidance on nesting vs. creating parents separately, stating which is preferable and why. This is textbook guidance on when and why to use the tool in a certain way.

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