Skip to main content
Glama
respanai

Respan MCP Server

Official
by respanai

create_experiment

Create and run an experiment that processes dataset rows through a workflow (prompt, model, or passthrough) and scores outputs with evaluator pipelines.

Instructions

Create and run an experiment. Processes a dataset's inputs through a workflow chain (prompt / model / passthrough) and scores results with evaluator pipelines.

REQUIRED: dataset_id, workflow, evaluator_workflow_ids.

WORKFLOW TYPES (these are how each dataset row produces an output):

  • "prompt": Use a saved prompt. Config: { prompt_id, version (optional) }

  • "completion": Direct model completion. Config: { model, temperature, max_tokens, top_p, response_format, tools, ... }

  • "duplicate": Passthrough — skip generation and just score the dataset's existing outputs. Use when your dataset already has outputs (e.g. logs imported from prod) and you only want to evaluate them.

  • "condition": Branch based on field values. Config: { condition_policy: { "event.": { operator, value } } }

EVALUATOR_WORKFLOW_IDS: Pass PIPELINE IDs (from list_evaluation_pipelines or create_evaluation_pipeline — the "id" field, NOT "workflow_id"). These pipelines score each row after the workflow completes.

EXAMPLE — Compare two models on a dataset: { "name": "GPT-4o vs Claude", "dataset_id": "ds_abc", "workflow": [ { "type": "completion", "config": { "model": "openai/gpt-4o", "temperature": 0 } } ], "evaluator_workflow_ids": [""] }

EXAMPLE — Score existing dataset outputs without re-running a model: { "name": "Score existing outputs", "dataset_id": "ds_with_outputs", "workflow": [ { "type": "duplicate", "config": { "name": "passthrough" } } ], "evaluator_workflow_ids": [""] }

EXAMPLE — Test a saved prompt version: { "name": "Prompt v3", "dataset_id": "ds_abc", "workflow": [ { "type": "prompt", "config": { "prompt_id": "prompt_xyz", "version": "3" } } ], "evaluator_workflow_ids": [""] }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoExperiment name.
workflowYesWorkflow tasks executed in order for each dataset row.
batch_sizeNoRows processed per batch (default: 100).
dataset_idYesDataset ID to run the experiment against.
concurrencyNoConcurrent workers (default: 15).
descriptionNoExperiment description.
enable_tracingNoCreate trace logs for each row (default: true).
evaluator_workflow_idsYesEvaluator PIPELINE IDs (the 'id' from list_evaluation_pipelines / create_evaluation_pipeline, NOT 'workflow_id'). At least one required.
Behavior3/5

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

With no annotations provided, the description must carry the burden of disclosing side effects. It mentions that the tool creates and runs an experiment, which implies resource usage and potential long-running operations, but it does not explicitly state any side effects, rate limits, or mutability constraints. The description is somewhat transparent but could be more explicit about the consequences of execution.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is quite verbose, with three examples that are largely similar and could be consolidated. While the use of headers and bullet points improves structure, the repetition makes it less concise. A more streamlined description would be easier to digest.

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 complexity of 8 parameters and 3 required, the description covers all parameters and provides clarification on ambiguous points (e.g., pipeline IDs vs workflow IDs). It also explains the workflow types and defaults. Since there is no output schema, it does not need to explain return values, but it provides sufficient context for usage.

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?

The description adds significant meaning beyond the input schema, especially for the 'workflow' parameter where it details each workflow type and configuration structure, and for 'evaluator_workflow_ids' where it clarifies that pipeline IDs must be used. It also provides examples that tie parameters together. The schema already covers basics, but the description enriches understanding.

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's purpose: to create and run an experiment that processes dataset inputs through a workflow chain and scores results with evaluator pipelines. It distinguishes itself from sibling tools like list_experiments and get_experiment by focusing on creation and execution.

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 detailed guidance on when to use the tool, including explanations of workflow types and the requirement for evaluator pipeline IDs. It includes multiple examples illustrating different configurations, which helps users understand how to apply it. However, it does not explicitly contrast with alternative tools, though the purpose is clear.

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/respanai/respan-mcp'

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