build_search_pipeline
Construct a multi-step pipeline for complex biomedical searches, chaining operations like search, link, and combine via the Entrez History Server.
Instructions
Build and execute a multi-step search pipeline.
Uses Entrez History Server to chain operations efficiently. Ideal for complex queries like: "Find diabetes reviews, then limit to articles linked to HLA genes"
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"steps": "<steps>"
},
"name": "build_search_pipeline"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| steps | Yes | List of pipeline steps, each with: - operation: "search", "link", or "combine" - database: Target database ("pubmed", "pmc", "gene", etc.) - parameters: Operation-specific params - search: {"query": "search terms"} - link: {"from_db": "pubmed", "link_name": "pubmed_gene"} - combine: {"combine_with": 1, "operator": "AND"} | |
| output_step | No | Step number to return results from |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||