Skip to main content
Glama
3a3

Fujitsu Social Digital Twin MCP Server

by 3a3

start_simulation

Start a traffic simulation using a dataset configuration; returns the simulation ID and initial status.

Instructions

Launches a new traffic simulation using the provided simulation dataset configuration, returning the simulation ID and initial status.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
simdata_idYes
ctxNo

Implementation Reference

  • The MCP tool handler for 'start_simulation'. Validates input, creates an HTTP client, delegates to the API client, and returns the result.
    @mcp.tool()
    async def start_simulation(simdata_id: str, ctx: Optional[Context] = None) -> Dict[str, Any]:
        """Launches a new traffic simulation using the provided simulation dataset configuration, 
        returning the simulation ID and initial status."""    
        try:
            if not simdata_id:
                return format_api_error(400, "simdataId required")
            
            async with await get_http_client() as client:
                api_client = FujitsuSocialDigitalTwinClient(client)
                result = await api_client.start_simulation(simdata_id)
            return result
        except Exception as e:
            logger.error(f"Simulation start error: {e}")
            return format_api_error(500, str(e))
  • The schema/interface is defined via the @mcp.tool() decorator and the function signature: takes simdata_id (str) and optional ctx, returns a dict.
    @mcp.tool()
    async def start_simulation(simdata_id: str, ctx: Optional[Context] = None) -> Dict[str, Any]:
        """Launches a new traffic simulation using the provided simulation dataset configuration, 
        returning the simulation ID and initial status."""    
        try:
            if not simdata_id:
                return format_api_error(400, "simdataId required")
            
            async with await get_http_client() as client:
                api_client = FujitsuSocialDigitalTwinClient(client)
                result = await api_client.start_simulation(simdata_id)
            return result
        except Exception as e:
            logger.error(f"Simulation start error: {e}")
            return format_api_error(500, str(e))
  • The @mcp.tool() decorator above the function registers it as an MCP tool named 'start_simulation'.
    @mcp.tool()
    async def start_simulation(simdata_id: str, ctx: Optional[Context] = None) -> Dict[str, Any]:
  • API client method 'start_simulation' that calls POST /api/simulations with {'simdataId': simdata_id}. Used by the handler and also by create_simulation_from_usecase.
    async def start_simulation(self, simdata_id: str) -> Dict[str, Any]:
        try:
            response = await self.client.post(
                "/api/simulations", 
                json={"simdataId": simdata_id}
            )
            response.raise_for_status()
            return format_simulation_result(response.json())
        except httpx.HTTPStatusError as e:
            logger.error(f"Simulation start error: {e}")
            return format_api_error(e.response.status_code, str(e))
        except Exception as e:
            logger.error(f"Unexpected error starting simulation: {e}")
            return format_api_error(500, str(e))
Behavior2/5

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

No annotations are provided, so the description must fully convey behavioral traits. It discloses that the tool returns an ID and status, but does not mention side effects (e.g., asynchronous nature, resource consumption, failure modes), permissions needed, or whether the simulation runs in the background. This is insufficient for an agent to understand the full impact.

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 a single sentence of 18 words, front-loading the action and result. It contains no redundant information and is efficiently structured.

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

Completeness2/5

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

Given the tool launches a simulation (a potentially long-running and state-changing operation), the description lacks critical details: synchronous vs. asynchronous, error handling, required preconditions (e.g., simdata_id must be valid), and return value structure. The absence of an output schema further burdens the description, making it incomplete.

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 0% schema description coverage, the description must clarify parameters. It implies simdata_id is the 'simulation dataset configuration', adding context beyond the schema's type-only definition. However, the 'ctx' parameter is not explained at all, and its purpose (optional context) is unclear from the description. Partial compensation.

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?

The description clearly states the tool launches a new traffic simulation, specifying the action (launches), resource (new traffic simulation), and output (simulation ID and initial status). It effectively distinguishes from sibling tools like analyze or compare, as this is the initialization step.

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 the tool is used when you have a simulation dataset configuration (simdata_id) and want to start a simulation, but it lacks explicit guidance on when to use it versus alternatives, such as create_simulation_from_usecase (which also creates simulations). No warnings or prerequisites are mentioned.

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/3a3/fujitsu-sdt-mcp'

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