Skip to main content
Glama
sniper35
by sniper35

check_instance_status

Monitor Verda Cloud GPU instance status and retrieve SSH connection details to verify operational state and accessibility.

Instructions

Check the status of a specific instance.

Args: instance_id: The ID of the instance to check.

Returns: Instance status details including SSH connection info if running.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
instance_idYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • Main handler function for the 'check_instance_status' MCP tool. Decorated with @mcp.tool() to register it as a tool. Takes an instance_id parameter and returns a formatted string with instance details including hostname, ID, status, type, IP address, and SSH connection info if available. Calls client.get_instance() to fetch instance data.
    @mcp.tool()
    async def check_instance_status(instance_id: str) -> str:
        """Check the status of a specific instance.
    
        Args:
            instance_id: The ID of the instance to check.
    
        Returns:
            Instance status details including SSH connection info if running.
        """
        client = _get_client()
        instance = await client.get_instance(instance_id)
    
        result = [
            f"# Instance: {instance.hostname}",
            f"- **ID**: `{instance.id}`",
            f"- **Status**: {instance.status}",
            f"- **Type**: {instance.instance_type}",
        ]
    
        if instance.ip_address:
            result.append(f"- **IP Address**: {instance.ip_address}")
            result.append("\n## SSH Connection")
            result.append("```bash")
            result.append(f"ssh root@{instance.ip_address}")
            result.append("```")
    
        return "\n".join(result)
  • Instance dataclass that defines the schema/structure for instance data returned by the tool. Contains fields: id, hostname, status, instance_type, ip_address, location, and startup_script_id. Includes a from_sdk() classmethod to convert SDK objects to this schema.
    @dataclass
    class Instance:
        """Simplified instance representation."""
    
        id: str
        hostname: str
        status: str
        instance_type: str
        ip_address: str | None
        location: str | None = None
        startup_script_id: str | None = None
    
        @classmethod
        def from_sdk(cls, inst: Any) -> "Instance":
            """Create from SDK Instance object."""
            return cls(
                id=inst.id,
                hostname=getattr(inst, "hostname", ""),
                status=getattr(inst, "status", "unknown"),
                instance_type=getattr(inst, "instance_type", ""),
                ip_address=getattr(inst, "ip", None),
                location=getattr(inst, "location", None),
                startup_script_id=getattr(inst, "startup_script_id", None),
            )
  • Helper method get_instance() in VerdaSDKClient that fetches instance details by ID. Called by the check_instance_status handler. Wraps the SDK's get_by_id call and converts the result to an Instance object using Instance.from_sdk().
    async def get_instance(self, instance_id: str) -> Instance:
        """Get instance details.
    
        Args:
            instance_id: Instance ID.
    
        Returns:
            Instance object.
        """
        self._ensure_client()
        inst = await self._run_sync(self._instances.get_by_id, instance_id)
        return Instance.from_sdk(inst)
Behavior2/5

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

With no annotations provided, the description carries full burden but offers minimal behavioral context. It mentions that returns include 'SSH connection info if running', which adds some value about conditional output. However, it doesn't disclose authentication needs, rate limits, error conditions, or what 'status' entails beyond SSH info, leaving significant gaps for a tool that presumably queries cloud infrastructure.

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 structured and concise: a clear purpose statement followed by well-organized Args and Returns sections. Every sentence earns its place, with no redundant or vague language. It's front-loaded with the core functionality.

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 moderate complexity (checking instance status in cloud infrastructure), the description is minimally adequate. The presence of an output schema means it doesn't need to detail return values, but with no annotations and incomplete behavioral context, it leaves the agent to guess about permissions, errors, and operational constraints. It meets the baseline for a read-only status check tool.

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 description coverage is 0%, but the description compensates well by explaining the single parameter 'instance_id' as 'The ID of the instance to check', adding clear meaning beyond the schema's generic 'Instance Id' title. Since there's only one parameter and the description covers it fully, this earns a high score despite the low schema coverage.

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 verb 'check' and the resource 'status of a specific instance', making the purpose unambiguous. It distinguishes from siblings like 'list_instances' (which lists multiple) and 'monitor_spot_availability' (which checks spot pricing). However, it doesn't explicitly differentiate from 'show_config' which might also show instance details, so it's not a perfect 5.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose this over 'list_instances' for status information, or whether it should be used before operations like 'start_instance' or 'delete_instance'. The agent must infer usage from the purpose alone.

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/sniper35/verda-cloud-mcp'

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