Skip to main content
Glama

create_experiment

Create a new CloudLab experiment from a specified profile to configure and deploy test environments for research or development projects.

Instructions

Create a new CloudLab experiment from a profile

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectYesProject name (e.g., 'UCY-CS499-DC')
profile_nameYesProfile name (e.g., 'small-lan')
profile_projectYesProject that owns the profile (e.g., 'PortalProfiles')
nameNoOptional experiment name (auto-generated if not provided)
bindingsNoOptional profile parameter bindings (e.g., {nodeCount: '2', phystype: 'c220g1'})

Implementation Reference

  • The handler function for the 'create_experiment' tool. It extracts parameters from the request, constructs the request body, calls the CloudLab API to create the experiment via POST /experiments, and returns the result.
    case "create_experiment": {
      const { project, profile_name, profile_project, name, bindings } = args as {
        project: string;
        profile_name: string;
        profile_project: string;
        name?: string;
        bindings?: Record<string, string>;
      };
      const body: Record<string, any> = {
        project,
        profile_name,
        profile_project,
      };
      if (name) body.name = name;
      if (bindings) body.bindings = bindings;
    
      const result = await cloudlabRequest("/experiments", "POST", body);
      return {
        content: [
          {
            type: "text",
            text: `Experiment created: ${JSON.stringify(result, null, 2)}`,
          },
        ],
      };
    }
  • The tool registration and input schema definition for 'create_experiment', including name, description, properties, and required fields for input validation.
    {
      name: "create_experiment",
      description: "Create a new CloudLab experiment from a profile",
      inputSchema: {
        type: "object",
        properties: {
          project: {
            type: "string",
            description: "Project name (e.g., 'UCY-CS499-DC')",
          },
          profile_name: {
            type: "string",
            description: "Profile name (e.g., 'small-lan')",
          },
          profile_project: {
            type: "string",
            description: "Project that owns the profile (e.g., 'PortalProfiles')",
          },
          name: {
            type: "string",
            description: "Optional experiment name (auto-generated if not provided)",
          },
          bindings: {
            type: "object",
            description: "Optional profile parameter bindings (e.g., {nodeCount: '2', phystype: 'c220g1'})",
          },
        },
        required: ["project", "profile_name", "profile_project"],
      },
    },
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 implies a write operation ('Create') but doesn't disclose critical traits like required permissions, whether creation is idempotent, typical response time, or what happens on failure (e.g., if the profile doesn't exist).

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, efficient sentence that front-loads the core purpose without unnecessary words. Every element ('new CloudLab experiment from a profile') directly contributes to understanding the tool's function.

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?

For a creation tool with 5 parameters, no annotations, and no output schema, the description is inadequate. It doesn't cover behavioral aspects (e.g., what the tool returns, error conditions), usage context, or compensate for the lack of structured metadata, leaving significant gaps for an AI agent.

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?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no additional meaning about parameters beyond what's in the schema (e.g., it doesn't explain relationships between 'profile_project' and 'project', or typical 'bindings' values).

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 ('Create') and resource ('new CloudLab experiment from a profile'), making the purpose immediately understandable. It distinguishes from siblings like 'get_experiment' or 'terminate_experiment' by specifying creation, though it doesn't explicitly differentiate from 'extend_experiment' which also modifies experiments.

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 prerequisites (e.g., needing an existing project or profile), when not to use it (e.g., for modifying existing experiments), or refer to sibling tools like 'extend_experiment' for updates.

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/ArdaGurcan/cloudlab-mcp'

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