MCP server for predicting molecular complex conformation and protein-ligand binding affinity using biochemical analysis
Single tool 'execute_skill_action' has a reasonable name starting with verb, but critical gaps undermine quality. Description is 97 chars (within 10-1024 range but minimal). Input schema present with two parameters (target_pdb_id, small_molecule_smiles), both with descriptions. However, no output schema is documented anywhere, the tool's return structure is completely undocumented. The mcp_server.py shows only a stub that prints a JSON status message; actual tool invocation logic is absent. Tool definition appears inferred from client.py rather than explicitly registered in the MCP server. No error handling, no validation guidance, no recovery paths. No tool annotations (readOnlyHint, destructiveHint, idempotentHint). The server does not implement the MCP protocol, it merely prints a status message and exits.
Execute biochemical protein-ligand binding affinity prediction skill action
No output schema documented. Tool returns complex object (screening_id, predicted_kd_binding_affinity_nm, docking_rmsd_angstroms, etc.) but LLM has no way to know what fields to expect or their types.
Tool definition not explicitly registered in MCP server code. mcp_server.py contains only a stub that prints status; actual tool invocation, parameter validation, and response handling are missing entirely.
No error handling or recovery guidance. Tool has no documented failure modes, validation rules, or actionable error messages. LLM cannot self-correct on invalid PDB IDs or malformed SMILES strings.
No tool annotations. Tool lacks readOnlyHint (appears to be read-only), destructiveHint, or idempotentHint. LLM cannot reason about side effects or retry safety.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 31 | 2026-07-28+ | v2 |
Description is minimal (97 chars). Does not explain WHEN to use this tool, what prerequisites exist (e.g., valid PDB ID format), or what the output represents. LLM cannot determine if this is the right tool for a given task.