Skip to main content
Glama

get_legal_actions

Retrieve legal actions for your unit: movable tiles, attackable enemies, healable allies, and wait option. Works only on READY or MOVED status units. Call before issuing move, attack, heal, or wait to avoid errors.

Instructions

Read-only. Return all legal actions for one of your units this turn: movable tiles, attackable enemy unit_ids, healable ally unit_ids, and whether wait is available. Only works on your own units in READY or MOVED status; returns an error for enemy units or units that have already acted. unit_id is the string identifier from get_state. Call this before issuing move, attack, heal, or wait to avoid illegal-action errors.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
connection_idYes
unit_idYes

Implementation Reference

  • Tool handler that validates the session is active and the unit belongs to the viewer, then delegates to legal_actions_for_unit. Wraps IllegalAction into ToolError.
    def get_legal_actions(session: Session, viewer: Team, unit_id: str) -> dict:
        _require_active(session, viewer)
        _require_own_unit(session.state, unit_id, viewer)
        try:
            return legal_actions_for_unit(session.state, unit_id)
        except IllegalAction as e:
            raise ToolError(str(e)) from e
  • Registration of get_legal_actions in the TOOL_REGISTRY with its input schema (requires unit_id string).
    "get_legal_actions": {
        "fn": get_legal_actions,
        "description": "Get the legal moves/attacks/heals/wait for one of your units.",
        "input_schema": {
            "type": "object",
            "properties": {"unit_id": {"type": "string"}},
            "required": ["unit_id"],
        },
    },
  • Import of get_legal_actions from read_only module into the tools package.
    from .read_only import (
        get_state,
        get_unit,
        get_unit_range,
        get_legal_actions,
        simulate_attack,
        get_threat_map,
        get_tactical_summary,
        get_history,
    )
  • Core logic: computes legal moves, attacks, and heals for a unit based on its status (READY/MOVED/DONE), reachable tiles, attack range, and heal adjacency.
    def legal_actions_for_unit(state: GameState, unit_id: str) -> dict:
        """Return the structured set of actions this unit can take right now.
    
        Keys:
          - status: current unit status
          - moves: list of {dest, cost} if unit can still move, else []
          - attacks: list of {target_id, from, damage, will_counter, counter_damage,
                              kills, counter_kills} reachable from current pos
                     PLUS from each reachable destination if the unit hasn't moved
          - heals: similar, only if unit.can_heal
          - can_wait: True unless the unit is already DONE
        """
        unit = state.units.get(unit_id)
        if unit is None or not unit.alive:
            raise IllegalAction(f"unit {unit_id} not found (dead, nonexistent, or hidden by fog)")
        if unit.owner is not state.active_player:
            raise IllegalAction(f"unit {unit_id} belongs to {unit.owner}, not active player")
    
        moves: list[dict] = []
        attacks: list[dict] = []
        heals: list[dict] = []
    
        if unit.status is UnitStatus.READY:
            reach = reachable_tiles(state, unit)
            moves = [
                {"dest": p.to_dict(), "cost": c}
                for p, c in sorted(reach.items(), key=lambda kv: (kv[1], kv[0].x, kv[0].y))
                if p != unit.pos
            ]
            origins = list(reach.keys())
        elif unit.status is UnitStatus.MOVED:
            origins = [unit.pos]
        else:  # DONE
            return {
                "unit_id": unit_id,
                "status": unit.status.value,
                "moves": [],
                "attacks": [],
                "heals": [],
                "can_wait": False,
            }
    
        # Enumerate attacks and heals from every valid origin tile.
        for origin in origins:
            # Attacks
            for enemy in state.units.values():
                if not enemy.alive or enemy.owner is unit.owner:
                    continue
                if not in_attack_range(origin, enemy.pos, unit.stats):
                    continue
                pred = predict_attack(
                    unit,
                    enemy,
                    attacker_tile=state.board.tile(origin),
                    defender_tile=state.board.tile(enemy.pos),
                    attacker_pos=origin,
                )
                attacks.append(
                    {
                        "target_id": enemy.id,
                        "from": origin.to_dict(),
                        "damage": pred.total_damage_to_defender,
                        "kills": pred.defender_dies,
                        "will_counter": pred.will_counter,
                        "counter_damage": pred.total_counter_damage,
                        "counter_kills": pred.attacker_dies,
                    }
                )
            # Heals
            if unit.stats.can_heal:
                for ally in state.units.values():
                    if not ally.alive or ally.owner is not unit.owner or ally.id == unit.id:
                        continue
                    if origin.manhattan(ally.pos) != 1:
                        continue
                    if ally.hp >= ally.stats.hp_max:
                        continue  # no effect; exclude
                    heal_amt = min(unit.stats.heal_amount, ally.stats.hp_max - ally.hp)
                    heals.append(
                        {
                            "target_id": ally.id,
                            "from": origin.to_dict(),
                            "heal_amount": heal_amt,
                        }
                    )
    
        return {
            "unit_id": unit_id,
            "status": unit.status.value,
            "moves": moves,
            "attacks": attacks,
            "heals": heals,
            "can_wait": True,
        }
Behavior4/5

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

Starts with 'Read-only' and describes return structure. Discloses error behavior for inappropriate units. No annotations, so description carries burden; missing details like rate limits or authentication, but sufficient.

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?

Four sentences with no fluff. Key purpose first, then usage guidance, then error conditions. Front-loaded efficiently.

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

Completeness5/5

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

No output schema, but description covers return values (tiles, enemy IDs, ally IDs, wait). Adequate for a query tool; includes prerequisites and error handling.

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

Parameters4/5

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

Schema coverage is 0%, but description clarifies unit_id as 'string identifier from get_state'. Adds meaning beyond schema, though connection_id is not explained.

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?

Clearly states it returns legal actions for a unit, listing specific action categories (movable tiles, attackable enemies, etc.). Distinguishes from sibling action tools like attack, move, heal, wait.

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

Usage Guidelines5/5

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

Explicitly advises calling before move/attack/heal/wait to avoid errors. Specifies conditions (own units in READY or MOVED) and error cases (enemy units or already acted).

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/haoyifan/Silicon-Pantheon'

If you have feedback or need assistance with the MCP directory API, please join our Discord server