google_research
Conduct deep multi-agent research on any topic, spawning parallel subagents for comprehensive coverage and producing a cited report with adaptive stopping.
Instructions
Perform extensive DEEP research on a topic using Anthropic's Multi-Agent Research Architecture.
This tool implements the FULL multi-agent system:
Lead Researcher (Orchestrator): Plans approach, coordinates subagents, synthesizes results
Search Subagents: Parallel workers for different aspects (spawned dynamically)
Citation Agent: Processes documents and inserts inline citations
Memory Module: Persists context, findings, and gaps across iterations
Process Flow:
Think (Plan Approach) - Decompose topic into aspects
Create Subagents - Spawn parallel workers for each aspect
Execute Research - Each subagent: web_search → think(evaluate) → complete_task
Think (Synthesize) - Combine findings, calculate coverage
Evaluate - "More research needed?" decision with adaptive stopping
Citation Agent - Process report and insert citations
Return Final Report
Depth Levels:
basic: 2 iterations max, 2 aspects, ~60% coverage threshold
moderate: 3 iterations max, 5 aspects, ~75% coverage threshold
comprehensive: 4 iterations max, 11 aspects, ~90% coverage threshold
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": {
"topic": "<topic>"
},
"name": "google_research"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| depth | No | moderate | |
| topic | Yes | Research topic | |
| max_content_per_page | No | Max content per page (default: 50000) |