manage_ui

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

With no annotations, the description carries the full burden. It discloses important behavioral traits: preview clones into CoreGui in Edit, click uses VirtualInput/attribute click with specific contexts, scroll targets ScrollingFrame CanvasPosition, and design_brief can conditionally build via create=true. However, some actions like check/get_abs/delete are not elaborated regarding side effects or return behavior, leaving gaps.

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 a single, dense sentence that front-loads the main purpose and then lists actions with parenthetical clarifications. It is concise and information-dense, but the one-sentence structure could be improved with bullet points for readability. Still, every word 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?

Given the tool's high complexity (13 params, many actions, nested trees, no output schema), the description covers the main action list and key operational contexts, which is substantial. However, it omits details on return values, prerequisites, and some actions (e.g., check, get_abs, update), so it is not fully complete.

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 38%, so the description adds meaning. It maps actions to parameters: design_brief uses 'brief' and 'create', preview/clicks/scroll explain PlayerGui/StarterGui context, and delta/canvasPosition are clarified. Yet several properties (path, parentPath, screenGuiName, depth, kind, properties, tree) are not described in the text, though some are self-explanatory.

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 'Create, inspect, preview, and interact with Roblox UI' with a specific verb+resource, clearly distinguishing it from sibling tools like manage_terrain or manage_lighting. It enumerates 14 concrete actions, leaving no ambiguity about the tool's scope.

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 implies it is the go-to tool for Roblox UI manipulation, and the action-specific notes (e.g., preview clones into CoreGui in Edit, click/scroll work in PlayerGui during playtest) give context on when each action applies. However, it does not explicitly state when to use it over alternatives like mutate_instances or query_instances, nor does it mention exclusions.

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