Skip to main content
Glama
using76
by using76

bulc_run_fds

Destructive

Start FDS fire simulation in the background for building design analysis, allowing users to monitor progress separately while the simulation runs.

Instructions

Start FDS simulation. Runs the simulation in background and returns immediately. Use bulc_get_fds_status to monitor progress.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
mpiProcessesNoNumber of MPI processes. Default: auto (based on mesh count)
openmpThreadsNoNumber of OpenMP threads per process. Default: 1
outputPathNoOutput directory. Default: BULC_result folder

Implementation Reference

  • Handler implementation for the 'bulc_run_fds' MCP tool. Validates input arguments using RunFdsSchema and sends a 'run_fds' command to the BULC client.
    case "bulc_run_fds": {
      const validated = RunFdsSchema.parse(args);
      result = await client.sendCommand({
        action: "run_fds",
        params: validated,
      });
      break;
    }
  • MCP tool schema definition for 'bulc_run_fds', including input schema, description, and annotations.
    {
      name: "bulc_run_fds",
      description:
        "Start FDS simulation. " +
        "Runs the simulation in background and returns immediately. " +
        "Use bulc_get_fds_status to monitor progress.",
      inputSchema: {
        type: "object" as const,
        properties: {
          mpiProcesses: {
            type: "integer",
            description: "Number of MPI processes. Default: auto (based on mesh count)",
          },
          openmpThreads: {
            type: "integer",
            description: "Number of OpenMP threads per process. Default: 1",
          },
          outputPath: {
            type: "string",
            description: "Output directory. Default: BULC_result folder",
          },
        },
      },
      annotations: {
        readOnlyHint: false,
        destructiveHint: true,
      },
    },
  • src/index.ts:112-121 (registration)
    Registration logic in main server that routes 'bulc_run_fds' tool calls to the handleFdsRunTool handler.
    if (
      name === "bulc_preview_fds" ||
      name === "bulc_validate_fds" ||
      name === "bulc_export_fds" ||
      name === "bulc_run_fds" ||
      name === "bulc_get_fds_status" ||
      name === "bulc_stop_fds"
    ) {
      return await handleFdsRunTool(name, safeArgs);
    }
  • Zod validation schema used for input validation in the bulc_run_fds handler.
    const RunFdsSchema = z.object({
      mpiProcesses: z.number().int().positive().optional(),
      openmpThreads: z.number().int().positive().optional(),
      outputPath: z.string().optional(),
    });
  • src/index.ts:48-48 (registration)
    Includes fdsRunTools (containing bulc_run_fds schema) in the allTools list registered with the MCP server.
    ...fdsRunTools,       // 6 tools: preview, validate, export, run, status, stop
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, indicating this is a write operation with potential destructive effects. The description adds valuable context about the asynchronous execution pattern (runs in background, returns immediately) and the monitoring workflow, which isn't captured in annotations. However, it doesn't elaborate on what 'destructive' means in this context or mention rate limits, auth needs, or error conditions.

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 perfectly concise with two sentences that each earn their place: the first states the core functionality and execution behavior, the second provides essential workflow guidance. There's zero wasted language, and the most critical information is front-loaded.

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?

Given the tool's complexity (asynchronous simulation execution with destructive potential), the description provides good context about the execution pattern and monitoring workflow. With annotations covering safety aspects and no output schema, the description appropriately focuses on behavioral characteristics rather than return values. It could be more complete by explaining what 'destructive' entails in this specific 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?

With 100% schema description coverage, the input schema already fully documents all three parameters with their types and default values. The description adds no additional parameter information beyond what's in the schema, so it meets the baseline expectation but doesn't provide extra value regarding parameter usage or semantics.

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 action ('Start FDS simulation') and resource ('FDS simulation'), distinguishing it from sibling tools like bulc_get_fds_status or bulc_stop_fds. However, it doesn't explicitly differentiate from other run tools like bulc_run_evac or bulc_run_aset_analysis, 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 Guidelines4/5

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

The description provides clear context by stating the simulation runs in background and returns immediately, and explicitly names bulc_get_fds_status as the monitoring tool. This gives good guidance on when to use this tool versus alternatives for progress checking, though it doesn't mention when NOT to use it or compare with other simulation tools.

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