manage_input

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

With no annotations, the description carries the burden of behavioral disclosure. It reveals implementation details (UserInputService:CreateVirtualInput vs VirtualInputManager, LastClick attribute) and explains what each simulated action does. It stops short of describing error handling, return values, or side effects.

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 with information but structured as a single run-on sentence with many parentheticals and clauses. It is not poorly sized, but better formatting (e.g., bullets) would improve readability and scannability.

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 complexity (10 parameters, 7 action types) and lack of output schema, the description covers the core behaviors and action distinctions well. It omits potential details like result values, failure modes, or whether input is simulated server-side or client-side, but the provided context is sufficient for basic 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?

The description adds meaning beyond the schema by mapping parameters to actions (e.g., click_at uses viewport pixels, click_path targets a PlayerGui GuiButton, walk_to uses a path/position). Since schema coverage is only 50%, this helps fill gaps, though not all parameters (x, y, text, duration) are explicitly defined in the description.

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 opens with 'Simulate input,' a specific verb+resource phrase, and enumerates distinct action types (walk_to, click_world, etc.) that clearly differentiate it from sibling tools like manage_terrain or query_instances. The scope is 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?

Provides concrete guidance for when to use specific actions (e.g., 'walk_and_click — use this to verify world clicks') and distinguishes playtest vs edit behavior for click_path. However, it does not explicitly contrast with sibling tools or state when not to use this tool.

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