Add a paper to a collection, addressed by collection_id OR collection_name (get-or-create by name — no need to look up an id first). Nest with "/": collection_name "AgentOPA/Formal" files the paper under an "AgentOPA" folder. MUTATES: also auto-saves the paper to the library. Idempotent (adding a paper already in the collection is a no-op). Requires SF_API_KEY.

Answer a question using ONLY the papers you've saved — a synthesis over your library (or one collection) with inline [arXiv-ID] citations. The inverse of find_gaps (which finds important work you're MISSING): ask_library reasons over what you HAVE. Optionally scope to one collection (collection_name OR collection_id); omit both to use your whole library. Read-only. Requires SF_API_KEY (it reads your saved set). Free accounts get 1 question/month; Pro raises this to 200/day.

Pull new matching papers since the last digest delivery, in the same shape as search_papers results. Optionally scope to one watch by watch_name OR watch_id; omit both for all watches. Read-only and idempotent — does NOT advance any watermark (only digest delivery does), so it is safe to call repeatedly (no mark-on-read). This is the in-session 'anything new on my watches?' pull. Requires SF_API_KEY.

Find the co-authorship neighborhood of one or more authors. Given a list of author_ids, returns edges {from, to, papers_count, last_collab_year} where 'from' is one of the input authors and 'to' is any co-author appearing on a shared paper within the window. Use for AC reviewer triage (find conflicts), disambiguating researchers (who do they actually work with?), or expanding an author seed into a research community. window_years defaults to 10. Result is capped at 500 edges, sorted by papers_count DESC.

Create a new named collection. MUTATES. If a collection with that name already exists, returns the existing one (get-or-create — never errors on duplicate). Use "/" to nest under a folder, e.g. "AgentOPA/Formal" — the folder is derived from the name, so there is no parent to create first. Requires SF_API_KEY.

Create a standing watch — evaluated daily against newly-indexed papers, surfacing new matches via the email digest and via check_watches. MUTATES. Get-or-create by name (re-creating with an existing name returns it unchanged — never errors on duplicate). TWO forms: (1) the v2 STRUCTURED filter via criteria (collections/authors/categories/text/has_code/min_novelty/similar, AND-composed) — the composable, agent-tunable form, recommended; tune it with preview_watch first, and edit later with update_watch. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. (2) a single legacy seed selector (q OR collection_name OR collection_id OR anchor_paper_id); if criteria is given it takes precedence. Requires SF_API_KEY.

Delete a watch, addressed by watch_id OR name. MUTATES. Idempotent: deleting a non-existent watch is a no-op (no error). To change a watch in place (rename / novelty_min / retarget criteria) use update_watch instead of delete-and-recreate. Requires SF_API_KEY.

Embed a text string into a 768-dim Gemini Flash vector. Use for HyDE-style retrieval: (1) write a hypothetical short paper that would perfectly answer the user's query, (2) embed it with task_type='RETRIEVAL_DOCUMENT' (default — matches the corpus embedding side), (3) pass the resulting embedding back through search-style tools to find real papers nearest to the hypothetical. task_type='RETRIEVAL_QUERY' matches the query side and is useful for direct user-query embedding without HyDE. Pro-only — requires an SF_API_KEY on a Pro account; anonymous and free callers get a 403 pro_required. Cost: ~$0.0001/call; rate-limited at 30/minute per API key.

Extract paper content from an arXiv paper's LaTeX source. Two modes: 'results' (default) returns 800 chars of results/experiments + 3 table captions. 'all' returns full paper sections (abstract, introduction, related work, method, results, conclusion) at up to 3000 chars each + 5 table captions. ~62% of arXiv papers have LaTeX source. May take a few seconds.

Two-mode author tool — replaces discover_authors and get_author. Provide exactly one of q or id. Q-MODE (q=...): search for researchers by topic or name — uses embedding similarity for topics ('efficient LLM inference'), fuzzy matching for names ('Yann LeCun'). Returns a list of matching authors with author_id, name, h_index, total_papers, primary_field, research_topics. ID-MODE (id=...): look up a single author profile by author_id (obtained from a previous q-mode call or from co_author_graph results). Returns h-index, total citations, global rank, primary field, novelty score distribution, research topics, code/venue scores, years active, and their top 10 papers by rank score.

Find important work you HAVEN'T saved, for a collection or topic — a 'what am I missing?' analysis. Returns two buckets: foundational_gaps (canonical citation-graph anchors in the niche, not in your library) and frontier_gaps (recent high-novelty work in the niche, not yet saved). Provide exactly one seed: collection_name OR collection_id OR topic. The backend derives the niche, runs lineage + recent-novelty search, and subtracts your saved set. Read-only. Requires SF_API_KEY (it needs your library to subtract) and is a Pro feature — free accounts receive an upgrade prompt.

Get the citation graph for a paper, sorted by citing-paper rank_score (highest-impact first). 'citing' = outgoing references this paper cites; 'cited_by' = incoming citations from other papers. Default response is a lean 12-field shape per paper — pass verbose=true for the full 28-field shape.

Returns CANDIDATE FOUNDATIONAL PAPERS for a research topic — cheap retrieval only, no synthesis. Ranks papers by a blend of citation count (0.6 weight, captures importance) and semantic similarity to your topic (0.4 weight). Use this to bootstrap a literature survey or get a fast sense of the landscape. For a synthesized orientation report (key concepts, open problems, reading order), use the /field-guide skill which calls this tool internally. Does not require a Pro API key — no LLM calls are made.

Returns the FOUNDATIONAL WORK FOR A PAPER'S NICHE via the citation graph — the relative question ('what is foundational for THIS paper's specific sub-field', often itself only modestly cited) rather than the obvious global landmarks. Anchors on the paper, takes its embedding neighbourhood as the niche, and ranks what the niche cites into three tiers: niche_roots (the niche-specific foundations, ranked by how specifically the neighbourhood builds on them — surfaces canonical anchors that semantic search misses), field_level (broader secondary foundations), and discipline (universal landmarks like Attention Is All You Need, collapsed out of the way). Each paper carries cited_by_in_niche evidence so the claim is grounded, not asserted. Use this to trace prior art / lineage for a paper, or to find the canonical methods a niche is built on. Complements get_field_orientation (which is topic-anchored and retrieval-only). No Pro key and no LLM calls required.

Get full details for one or more papers by arXiv ID. Pass a single-element array for one paper; pass multiple IDs to batch-fetch up to 50 papers in one call (replaces the removed batch_lookup tool). Pass format='bibtex' to get a .bib citation entry (replaces the removed export_bibtex tool — bibtex is single-paper only; for multi-paper bibtex, call repeatedly). Default returns a lean 14-field shape (arxiv_id, title, authors, year, categories, has_code, github_url, citation_count, venue_name, llm_summary, llm_significance, llm_novelty_score, impact_pct, impact_tier — where impact_pct is the ML-forecast per-category impact percentile 0-100 and impact_tier its A+/A/B/C/D grade; both NULL on older papers outside the recent scoring window). Pass verbose=true for the full shape with structured extraction (method_name, contribution_type, task_category, datasets, baselines) and institution_tags. Use fields='arxiv_id,title,abstract' to select an exact subset, or fetch_fulltext with sections='all' for the full paper.

Like a paper — a 'more like this' calibration signal that tunes the user's For You feed toward similar work. INSERT-only and idempotent (liking twice is a no-op, never un-likes). Distinct from save_paper: like expresses taste for ranking; save bookmarks for later reading. Requires SF_API_KEY.

List the authenticated user's collections (named groups of saved papers) with paper counts. Read-only. Use before add_to_collection to see existing collections. Requires SF_API_KEY.

List the authenticated user's saved papers (their library), newest first. Read-only. Use this to review a reading list or to see what's already saved before saving more. Requires SF_API_KEY.

List the authenticated user's watches with name, a one-line definition summary, last_evaluated_at, and pending_hits (count of new matches since the last digest delivery). Read-only. Use before create_watch to see what's already tracked. Requires SF_API_KEY.

Dry-run a structured filter over recent papers WITHOUT creating a watch — the tuning loop. Returns {window_days, needs_similarity, match_count, sample} so you can iterate (add a category, raise min_novelty, switch the collection relation) before saving with create_watch. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. NOTE: for a similarity filter, match_count is capped at 200 (the cosine fetch window) and so saturates at 200 on broad/hot topics — tune by the sample scores and narrow with categories/min_novelty (or a higher similar floor) rather than relying on match_count alone. Read-only. Requires SF_API_KEY.

Remove a paper from a collection, addressed by collection_id OR collection_name. MUTATES (the paper stays in your library; it's only removed from this collection). Idempotent. Requires SF_API_KEY.

Save a paper to the authenticated user's Scholar Feed library (bookmark). MUTATES the library and feeds the user's personalization — saved papers are the strongest signal in the For You feed and the email digest. Idempotent: calling it again on an already-saved paper leaves it saved. Requires SF_API_KEY. To file it into a named collection in one step, use add_to_collection (that also saves).

Search Scholar Feed's 600k+ CS/AI/ML paper corpus. Defaults to semantic (embedding) search — finds conceptually related papers even when the user's wording doesn't match the paper's title/abstract. Pass mode='keyword' for exact-string full-text search. CAVEAT: semantic search often misses old high-citation CANONICAL papers (e.g. foundational anchors like H2O for KV eviction, GRIT for unified embedding+generation) because the ranker prefers recent stylistically-matched papers. If you're hunting the canonical anchor for an area, parse the top-5 result abstracts for baseline mentions ('we compare against X, Y, Z'), then look the most-mentioned name up directly. Returns papers with LLM-generated summaries, novelty scores, and structured extraction data. Default response is a lean 14-field shape (arxiv_id, title, authors, year, categories, has_code, github_url, citation_count, venue_name, llm_summary, llm_significance, llm_novelty_score, impact_pct, impact_tier) — pass verbose=true or fields=... for the full shape with method/task/dataset extraction. RANKING BY IMPACT — two different notions, don't confuse them: (1) PROVEN impact = citations. For 'the important/seminal papers on topic X', pass sort='impactful' (most-cited among the relevant) or sort='balanced' (relevant AND well-cited). This is the right tool for established/foundational work. (2) FORECAST impact = impact_pct (0-100), an ML per-category percentile of PREDICTED citations, only computed for the last ~90 days; impact_tier is its A+/A/B/C/D grade. For 'what's rising/new in X' pass sort='trending' or filter impact_min=N — but NOTE impact_pct is NULL on everything older than ~90 days, so impact_min DROPS all established/canonical papers (it is NOT a way to find the influential papers in a niche — use sort='impactful' for that). Both impact notions are distinct from llm_novelty_score (new-idea-ness, an orthogonal filter). (3) ADOPTION impact = GitHub traction. Pass sort='community' to rank by real-world engineering adoption (stars + star-velocity) — the papers practitioners are actually running/building on, independent of citations or recency. Filter on it with min_stars=N (minimum GitHub stars) and has_code=true (only papers with a code release); has_code/min_stars surface RUNNABLE/ADOPTED work, the engineering counterpart to citations. github_url_exists=true is the stricter has_code (requires a linked repo). Supports filtering by category, novelty, recency, method, task, dataset, and contribution type — plus min_citations (minimum PROVEN citations, keeps established papers unlike the ~90-day impact_min) and an explicit date window via published_after / published_before ('YYYY-MM-DD', vs days' rolling lookback). v3 ABSORPTIONS: pass sort='trending' to rank by rising/forecast impact (impact_pct); pass anchor_paper_id to replicate find_similar (q is ignored in anchor mode, results carry similarity_score); pass scope_to_citations_of to restrict search to a paper's citation graph (replaces find_citations_about).

Remove a paper from the authenticated user's Scholar Feed library. MUTATES the library. Idempotent: removing a paper that isn't saved leaves it unsaved. Note: the saved library is a superset of all collections, so un-saving a paper ALSO removes it from every collection it was in. To keep it filed in a collection, use remove_from_collection instead (that leaves the paper saved). Requires SF_API_KEY.

Update an existing watch in place — rename, change novelty_min, or RETARGET its structured filter criteria. MUTATES. Address by watch_id OR name. Changing criteria replaces the definition and clears the watch's pending hits (so stale matches don't deliver); the next daily eval repopulates. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. Tune the new criteria with preview_watch first. Requires SF_API_KEY.