Call a method, remote or signal

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds real behavioral context beyond them: that effects can propagate to the server, that fire_remote on a RemoteFunction returns the InvokeServer answer, and that a client connection is required. It does not say what a 'method' call returns or whether failures are surfaced as errors, which is the remaining gap.

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 action taxonomy is front-loaded in the first sentence, and the safety warning and state requirement close it out, so structure is sound. The middle sentence is a long run-on parenthetical packing all the __type formats, which is dense but every clause carries information an agent needs to build args.

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 six-parameter mutation tool with no output schema, the description covers the action semantics, the argument encoding, the server-side risk, and the connection prerequisite. Only the return behavior of the 'method' and 'fire_signal' actions is left unstated, a minor omission given annotations already flag the destructive profile.

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 coverage is 100%, but the schema itself defers the Roblox value encoding to the description ('see the tool description'), so the description carries the real payload spec: concrete __type examples for Vector3, Vector2, Color3, CFrame, Enum and Instance, plus the note that null is unsupported. It also ties 'method' and 'signal' to their respective actions. The 'client' parameter's relationship to list_clients is left only in the schema, so it is not a full 5.

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 a specific verb+resource ('Act on the running game directly') and enumerates the three concrete actions with examples: method (FindFirstChild, Destroy), fire_remote (FireServer/InvokeServer), fire_signal (MouseButton1Click). An agent can map an intent onto the right action. It does not, however, distinguish itself from overlapping siblings such as execute_lua or gui_interact, which is what keeps it short of a 5.

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?

It gives an explicit precondition ('Requires the connected state') and a clear usage restriction ('only do it when the user asked for it'), which is meaningful guidance for a destructive tool. It stops short of naming alternatives – e.g. that arbitrary code should go to execute_lua or GUI clicking to gui_interact – so the agent must infer the boundary.

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