Decomposes natural language queries into targeted searches across Readwise Reader documents, highlights, and tags. Use when the user searches their reading library, asks what they saved about a topic, or wants to find specific highlights.
The search intelligence behind Readwise Reader queries. Transforms a natural language question into targeted searches across your reading library and produces ranked, relevant results.
Turn this:
"What articles have I saved about distributed systems that I highlighted?"
Into targeted searches:
Documents: search_library("distributed systems", limit=30)
Highlights: search_highlights("distributed systems", limit=20)
Tags: get_documents_by_tag("distributed-systems")
Then synthesize into a prioritized knowledge brief.
| Query Type | Example | Strategy |
|---|
| Topic search | "articles about X" | Broad document search + highlight search |
| Recall | "that article I saved about X" | Search titles and summaries, prioritize recent saves |
| Highlight retrieval | "my notes on X" | Prioritize highlight search, include annotations |
| Tag browse | "everything tagged X" | Tag-based document lookup |
| Status query | "what's in my inbox" | Location-filtered document list |
| Cross-reference | "X related to Y" | Multiple searches, intersect results |
From the query, extract:
For each query type, determine which tools to call and in what order:
Topic search:
search_library(query, category?, limit=30) -- broad document searchsearch_highlights(query, limit=20) -- parallel highlight searchRecall search:
search_library(query, limit=20) -- focus on titlesTag browse:
list_tags() -- find matching tag keysget_documents_by_tag(tag) -- fetch tagged documents| Factor | Weight | Description |
|---|---|---|
| Highlight count | 0.3 | Documents you highlighted are more valuable |
| Recency | 0.25 | More recently saved/updated items rank higher |
| Title/summary match | 0.25 | Direct keyword match in title or summary |
| Reading progress | 0.1 | Partially read items may be more relevant than unread |
| Tag match | 0.1 | Exact tag match boosts relevance |
For knowledge retrieval:
Highlighted + annotated documents > Highlighted documents > Read documents > Saved but unread
When initial search returns too few results:
Edit PDFs with natural-language instructions using the nano-pdf CLI.