Search the web using Google Custom Search API. Returns a list of URLs with titles and snippets.

When to use:

• You need URLs to process yourself (e.g., selective scraping)

• You only need links without full content

• You want to filter/choose which URLs to scrape

When to use search_and_scrape instead:

• You need actual page content for research

• You want content from multiple sources combined

Caching: Results cached for 30 minutes.

Extract text content from a URL. Automatically handles: web pages (static + JavaScript-rendered), YouTube videos (extracts transcript), and documents (PDF, DOCX, PPTX).

When to use:

• You already have a specific URL to extract content from

• Need content from YouTube videos, PDFs, or Office documents

• Want to check page structure before fetching full content (preview mode)

When to use search_and_scrape instead:

• Researching a topic across multiple sources

Content size control:

• max_length: Limit response size (default: server max of 50KB)

• mode: 'full' returns content, 'preview' returns metadata + structure only

Preview mode benefits:

• Check content size before fetching full content

• Get page structure (headings) to decide which sections to read

• Avoid context exhaustion with very large pages

Caching: Results cached for 1 hour.

Search Google AND retrieve content from top results in one call. Returns combined, deduplicated content with source attribution.

When to use:

• Primary tool for answering questions that need web research

• Need content from multiple sources combined

• More efficient than calling google_search + scrape_page separately

When to use other tools instead:

• google_search: When you only need URLs without content

• scrape_page: When you already have a specific URL

Content size control:

• max_length_per_source: Limit content per source (default: 50KB)

• total_max_length: Limit total combined content (default: 300KB)

• filter_by_query: Only include paragraphs containing query keywords

Caching: Search results cached for 30 minutes, scraped pages for 1 hour.

Search for images using Google Custom Search API. Returns image URLs, thumbnails, dimensions, and source page URLs.

When to use:

• Finding visual content — photos, illustrations, graphics, diagrams

• Need specific image formats, sizes, or color types

Key parameters:

• size: huge, large, medium, small

• type: clipart, face, lineart, photo, animated

• color_type: color, gray, mono, trans (transparent)

• file_type: jpg, gif, png, svg, webp

Caching: Results cached for 30 minutes.

Search for recent news articles with freshness filters and date sorting.

When to use:

• Current events, breaking news, time-sensitive topics

• Need headlines and snippets from news sources

• Want to restrict by publication date

When to use scrape_page instead:

• You need the full article content

Key parameters:

• freshness: hour, day, week, month, year (default: week)

• sort_by: relevance or date

• news_source: Restrict to specific domain (e.g., 'bbc.com')

Caching: Results cached for 30 minutes.

Track multi-step research progress across multiple API calls.

When to use:

• Complex investigations requiring 3+ searches with different angles

• Research you might abandon early (tracks partial progress)

• Investigations where you need to show reasoning steps

• Research with branching paths to explore alternatives

When to use search_and_scrape instead:

• Simple queries that need content from multiple sources in one call

Key principle: You do the reasoning; this tool tracks state. It persists across API calls so you can build on previous steps.

Example flow:

1. Start: sequential_search(searchStep: "Starting research on X", stepNumber: 1, nextStepNeeded: true)

2. Search: search_and_scrape("topic")

3. Record: sequential_search(searchStep: "Found Y, need Z", stepNumber: 2, source: {...}, nextStepNeeded: true)

4. Complete: sequential_search(searchStep: "Research complete", stepNumber: 3, nextStepNeeded: false)

Search academic papers using Google Custom Search API.

When to use:

• Finding peer-reviewed, authoritative sources

• Research requiring citations and references

• Technical/scientific topics and literature reviews

Features:

• Paper titles, authors, abstracts

• Publication years and venues

• Direct PDF links (when available)

• Pre-formatted citations (APA, MLA, BibTeX)

Academic sources: arXiv, PubMed, IEEE, Nature, Springer, ResearchGate, JSTOR, and more.

Caching: Results cached for 30 minutes.

Search patents using Google Custom Search API (site:patents.google.com).

When to use:

• Prior art search before filing

• Freedom to operate (FTO) analysis

• Patent landscaping and competitive intelligence

• Tracking innovation in specific domains

Features:

• Patent titles, numbers, abstracts

• Inventors and assignees

• Filing and publication dates

• Direct links to Google Patents and PDFs

• Filter by patent office (USPTO, EPO, WIPO, JPO, CNIPA, KIPO)

• Assignee search with automatic name variations

Important limitation: Google Custom Search doesn't index ALL patents. For comprehensive company patent research:

1. Use this tool for initial discovery with technology keywords

2. Use scrape_page on patents.google.com/?assignee=CompanyName for more complete results

3. Try multiple variations: company names without spaces, previous names, inventor names

4. Note that patents may be assigned to parent companies or subsidiaries

Search types:

• prior_art: Find related existing patents

• specific: Look up specific patent(s)

• landscape: Broad overview of a technology area

Caching: Results cached for 30 minutes.