Simple Google search for quick lookups. Returns snippets only. For deep research with full page content, use google_research or deep_search instead.

Performs a comprehensive web search by querying Google, fetching the FULL content from top results using advanced content extraction (Readability algorithm), and returning consolidated content. Supports web, news, and image search types. Includes retry logic for reliability.

This is TRUE deep research - it actually READS the pages, not just snippets.

Searches for recent news articles on a topic, fetches full article content, and returns consolidated results. Optimized for news and current events.

Perform extensive DEEP research on a topic using Anthropic's Multi-Agent Research Architecture.

This tool implements the FULL multi-agent system:

1. Lead Researcher (Orchestrator): Plans approach, coordinates subagents, synthesizes results

2. Search Subagents: Parallel workers for different aspects (spawned dynamically)

3. Citation Agent: Processes documents and inserts inline citations

4. Memory Module: Persists context, findings, and gaps across iterations

Process Flow:

1. Think (Plan Approach) - Decompose topic into aspects

2. Create Subagents - Spawn parallel workers for each aspect

3. Execute Research - Each subagent: web_search → think(evaluate) → complete_task

4. Think (Synthesize) - Combine findings, calculate coverage

5. Evaluate - "More research needed?" decision with adaptive stopping

6. Citation Agent - Process report and insert citations

7. 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

Fetch and extract the full readable content from a single URL. Uses Readability-style extraction to get the main content, removing navigation, ads, etc.

Create or manage a research session for multi-step research workflows.

Actions:

• create: Start a new session with Lead Researcher planning

• status: Check session progress, subagents, and coverage

• complete: Generate final report with citations

Add a source to a research session after fetching its content.

Search the web with source quality scoring. For full page content, follow up with fetch_page or use deep_search.

Get formatted citations from a research session. Supports markdown, numbered, and APA formats.

Manually spawn and run a subagent for a specific research aspect. This allows fine-grained control over the multi-agent research process.

The subagent will:

1. Generate queries for the aspect

2. Execute web searches

3. Fetch full page content

4. Evaluate findings

5. Return results

Evaluate the current research coverage and identify gaps. This implements the "More research needed?" decision point from Anthropic's architecture.