Skip to main content
Glama

submit_pose_analysis_md_workflow

Run molecular dynamics simulations to analyze protein-ligand binding pose stability, calculate binding free energies, and validate docking results through dynamic simulations.

Instructions

Submit a pose analysis molecular dynamics workflow using Rowan v2 API.

IMPORTANT: The protein parameter must be a UUID (36-character string) of an existing protein in your Rowan account. You cannot use PDB IDs directly. Use the create_protein_from_pdb_id tool first to create a protein, then use its UUID here.

Args: protein: UUID of an existing protein (e.g., "abc123-def456-..."). Get this from create_protein_from_pdb_id or from a previous workflow initial_smiles: SMILES string of the ligand molecule num_trajectories: Number of independent MD simulations to run (default: 1) simulation_time_ns: Simulation time in nanoseconds per trajectory (default: 10ns) ligand_residue_name: Residue name for the ligand in PDB structure (default: "LIG") name: Workflow name for identification and tracking folder_uuid: UUID of folder to organize this workflow. Empty string uses default folder. max_credits: Maximum credits to spend on this calculation. 0 for no limit.

Runs molecular dynamics simulations on protein-ligand complexes to:

  • Assess binding pose stability over time

  • Calculate binding free energies

  • Analyze protein-ligand interactions

  • Validate docking results with dynamics

Returns: Workflow object representing the submitted workflow

Examples: # Step 1: First create a protein from PDB ID protein_obj = create_protein_from_pdb_id( name="CDK2 Protein", code="1HCK" ) protein_uuid = protein_obj.uuid # Get the UUID

# Step 2: Run MD simulation with the protein UUID
result = submit_pose_analysis_md_workflow(
    protein=protein_uuid,  # Use the UUID from step 1
    initial_smiles="CCC(C)(C)NC1=NCC2(CCC(=O)C2C)N1",
    num_trajectories=1,
    simulation_time_ns=10,
    name="CDK2 Ligand MD"
)

# Or use a protein UUID from list_proteins() output
result = submit_pose_analysis_md_workflow(
    protein="550e8400-e29b-41d4-a716-446655440000",  # UUID format
    initial_smiles="CCO",
    num_trajectories=1,
    simulation_time_ns=5,
    name="Quick MD Validation"
)

This workflow can take 1-3 hours depending on simulation length.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
proteinYesProtein UUID (36-char string) of existing protein. Use create_protein_from_pdb_id first if needed
initial_smilesYesSMILES string of the ligand molecule
num_trajectoriesNoNumber of independent MD trajectories to run
simulation_time_nsNoSimulation time in nanoseconds for each trajectory
ligand_residue_nameNoResidue name for the ligand in the protein structureLIG
nameNoWorkflow name for identification and trackingPose-Analysis MD Workflow
folder_uuidNoUUID of folder to organize this workflow. Empty string uses default folder
max_creditsNoMaximum credits to spend on this calculation. 0 for no limit
Behavior4/5

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

With no annotations provided, the description carries full burden and does well: it discloses that the workflow 'can take 1-3 hours depending on simulation length' (performance expectation), mentions credit usage via max_credits parameter, and implies computational resource consumption. However, it doesn't explicitly state whether this is a read-only or destructive operation, or if it requires specific permissions.

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

Conciseness4/5

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

Well-structured with purpose upfront, important warnings highlighted, parameter details organized, and examples provided. Some redundancy exists between the 'Args' section and schema, but overall it's efficiently organized. The runtime warning at the end is appropriately placed.

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?

For a complex workflow tool with 8 parameters, no annotations, and no output schema, the description provides substantial context: purpose, prerequisites, parameter guidance, examples, and runtime expectations. It could be more complete by explicitly stating the operation type (read/write) and any authentication requirements, but it covers most essential aspects well.

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 8 parameters thoroughly. The description repeats parameter information in the 'Args' section but adds minimal value beyond what's in the schema. The baseline of 3 is appropriate since the schema does the heavy lifting, though the description does provide helpful context about the protein UUID requirement.

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: 'Submit a pose analysis molecular dynamics workflow using Rowan v2 API' with specific outcomes like assessing binding pose stability, calculating binding free energies, analyzing interactions, and validating docking results. It distinguishes from siblings by focusing on MD simulations for protein-ligand complexes, unlike tools like submit_docking_workflow or submit_admet_workflow.

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

Usage Guidelines5/5

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

Explicit guidance is provided: 'IMPORTANT: The protein parameter must be a UUID... You cannot use PDB IDs directly. Use the create_protein_from_pdb_id tool first to create a protein, then use its UUID here.' This clearly states when to use this tool (after protein creation) and references an alternative (create_protein_from_pdb_id) for prerequisite steps.

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/k-yenko/rowan-mcp'

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