Skip to main content
Glama
using76
by using76

bulc_place_evac_agents

Destructive

Place evacuation agents in building simulations to analyze emergency scenarios. Distribute agents randomly by count or position them at specific coordinates for fire safety planning.

Instructions

Place evacuation agents in rooms or at specific positions. Can place by count (random distribution) or at exact coordinates.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
roomNoRoom name or ID to place agents in
levelNoFloor level index. Default: current level
countNoNumber of agents to place randomly. Required if no positions given.
positionsNoSpecific positions as [[x1,y1], [x2,y2], ...] in cm. Alternative to count.
agentRadiusNoAgent radius in meters. Default: 0.25
desiredSpeedNoDesired walking speed in m/s. Default: 1.2
maxSpeedNoMaximum walking speed in m/s. Default: 1.5
minSpacingNoMinimum spacing between agents in meters. Default: 0.5

Implementation Reference

  • Handler logic for the 'bulc_place_evac_agents' tool: validates input using Zod schema and sends 'place_evac_agents' command to the BULC client.
    case "bulc_place_evac_agents": {
      const validated = PlaceEvacAgentsSchema.parse(args);
      result = await client.sendCommand({
        action: "place_evac_agents",
        params: validated,
      });
      break;
  • Zod schema for validating inputs to the 'bulc_place_evac_agents' tool.
    const PlaceEvacAgentsSchema = z.object({
      room: z.string().optional(),
      level: z.number().int().optional(),
      count: z.number().int().positive().optional(),
      positions: z.array(z.array(z.number()).length(2)).optional(),
      agentRadius: z.number().positive().optional(),
      desiredSpeed: z.number().positive().optional(),
      maxSpeed: z.number().positive().optional(),
      minSpacing: z.number().positive().optional(),
    });
  • Tool definition including name, description, and input schema for MCP registration.
    {
      name: "bulc_place_evac_agents",
      description:
        "Place evacuation agents in rooms or at specific positions. " +
        "Can place by count (random distribution) or at exact coordinates.",
      inputSchema: {
        type: "object" as const,
        properties: {
          room: {
            type: "string",
            description: "Room name or ID to place agents in",
          },
          level: {
            type: "integer",
            description: "Floor level index. Default: current level",
          },
          count: {
            type: "integer",
            description: "Number of agents to place randomly. Required if no positions given.",
          },
          positions: {
            type: "array",
            description: "Specific positions as [[x1,y1], [x2,y2], ...] in cm. Alternative to count.",
            items: {
              type: "array",
              items: { type: "number" },
            },
          },
          agentRadius: {
            type: "number",
            description: "Agent radius in meters. Default: 0.25",
          },
          desiredSpeed: {
            type: "number",
            description: "Desired walking speed in m/s. Default: 1.2",
          },
          maxSpeed: {
            type: "number",
            description: "Maximum walking speed in m/s. Default: 1.5",
          },
          minSpacing: {
            type: "number",
            description: "Minimum spacing between agents in meters. Default: 0.5",
          },
        },
      },
      annotations: {
        readOnlyHint: false,
        destructiveHint: true,
      },
  • End of evacTools array where the tool is registered in the list of tools.
    ];
Behavior4/5

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

Annotations indicate destructiveHint=true and readOnlyHint=false, confirming this is a write operation that modifies state. The description adds valuable context beyond annotations: it specifies that placement can be 'random distribution' or 'at exact coordinates,' and implies that either 'count' or 'positions' must be provided. This clarifies behavioral aspects not covered by annotations, though it doesn't detail side effects like overwriting existing agents or interaction with other tools.

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?

The description is extremely concise and front-loaded, consisting of a single sentence that directly states the tool's purpose and key functionality. Every word earns its place, with no redundant or vague phrasing. It efficiently communicates the core action and options without unnecessary detail.

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

Completeness3/5

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

Given the tool's complexity (destructive operation with 8 parameters) and lack of output schema, the description is minimally adequate. It covers the basic purpose and placement modes but doesn't address important contextual details like prerequisites (e.g., must agents be defined first?), effects on existing agents, or relationship to other evacuation tools. With annotations providing safety context, the description meets minimum viability but leaves gaps in operational context.

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?

The input schema has 100% description coverage, providing clear documentation for all 8 parameters. The description adds minimal semantic value beyond the schema, only hinting at the 'count' vs. 'positions' alternative usage. Since the schema already fully describes parameters, the baseline score of 3 is appropriate, as the description doesn't significantly enhance parameter understanding.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Place evacuation agents in rooms or at specific positions.' It specifies the verb ('place') and resource ('evacuation agents'), and distinguishes placement methods ('by count' vs. 'at exact coordinates'). However, it doesn't explicitly differentiate from sibling tools like 'bulc_set_agent_properties' or 'bulc_list_evac_agents', which prevents a perfect score.

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

Usage Guidelines3/5

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

The description implies usage context by mentioning two placement modes ('by count' or 'at exact coordinates'), but it doesn't provide explicit guidance on when to use this tool versus alternatives. For example, it doesn't clarify if this is for initial setup versus runtime adjustments, or how it relates to tools like 'bulc_set_agent_properties'. The guidance is present but limited to operational modes rather than broader context.

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/using76/BULC_MCP'

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