Skip to main content
Glama

Move the local character

character_control

Moves the local player's character to a world position, another player, or an instance path by teleporting instantly or walking with an arrival timeout and optional vertical offset.

Instructions

Move the local player's character. action teleport puts it at the target at once; action walk_to makes it walk there with the humanoid (it stops when it arrives, gets stuck or the timeout passes). The target is one of: position ({x,y,z}), player (another player's name, display name or user id) or path (a dotted path to a part or model). Near a player or instance the character lands offset_y studs above it (default 3). Teleporting can trigger anti-cheat in some games, so only do it when the user asked. Requires the connected state.

Input Schema

NameRequiredDescriptionDefault
pathNoGo to this part or model (dotted path starting at game).
actionYesteleport or walk_to.
clientNoClient id from list_clients, for example c2. Defaults to the client that connected last.
playerNoGo to this other player.
timeoutNowalk_to: seconds to wait for the character to arrive (default 10).
offset_yNoStuds above the player or instance (default 3).
positionNoWorld position to go to.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare this is mutating but not read-only, not idempotent, and closed-world, so the bar is lower; the description still adds real value by disclosing the walk_to termination conditions, the anti-cheat side effect of teleporting, and the connected-state prerequisite. It omits failure behavior (invalid path, no client, arrival failure) and what the call reports back.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core action, then the mode split, then the target forms, then the caveat and precondition. Five dense sentences with no filler; even the parenthetical defaults earn their space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter mutation tool with no output schema, the description covers the essentials: state requirement, mode semantics, timeout behavior, offset default, and the risk caveat. What is missing is what happens when the character cannot reach the target or when no client is connected, but the 100% schema coverage absorbs most of the remaining burden.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents action, timeout, offset_y, position, player, path, and client. The description restates the target options and repeats offset_y's default of 3, adding only the exclusivity framing that the three target parameters are mutually exclusive choices.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Move the local player's character') and immediately enumerates the two modes, so an agent can tell it apart from any sibling such as execute_lua or set_property without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear intra-tool guidance: teleport is instant, walk_to is gradual and terminates on arrival, stuck, or timeout, plus an explicit when-not ('only do it when the user asked' because of anti-cheat) and a precondition ('Requires the connected state'). It does not compare against sibling tools, which keeps it short of a 5.

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