Structured filter search — artworks matching ALL given filters (subject, material, technique, date, place, person). Returns artwork summaries with titles, creators, and dates; every response includes totalResults (exact match count, not just the returned page). Not for free-text concept queries — use semantic_search for those. Not for artwork-to-artwork similarity — use find_similar with an objectNumber. For demographic person queries (gender, born/died, profession, birth/death place), use search_persons first to get a vocabId, then pass it as creator here. For provenance text and ownership history, use search_provenance. For aggregate counts and distributions, prefer collection_stats — one call vs compact=true loops.

Ranking: relevance (BM25) when text search (description, title, etc.) or geographic proximity is used; otherwise importance (image availability, curatorial attention, metadata richness). For concept-ranked results, use semantic_search.

At least one filter is required. There is no full-text search across all metadata. For concept or thematic searches (e.g. 'winter landscape', 'smell', 'crucifixion'), ALWAYS start with subject — it searches ~832K artworks tagged with structured Iconclass vocabulary and has by far the highest recall for conceptual queries. Use description for cataloguer observations (compositional details, specific motifs); use curatorialNarrative for curatorial interpretation and art-historical context. These three corpora can return complementary results. For broader concept discovery beyond structured vocabulary, use semantic_search — but combine it with search_artwork(type: 'painting', …) for painting queries since paintings are underrepresented there.

Array values are AND-combined (e.g. subject: ['landscape', 'seascape'] finds artworks with both). If many results share an object-number prefix (e.g. multiple folios of one sketchbook), a warnings note flags it; narrow with type/material filters or treat the shared prefix as the unit. Each result carries an objectNumber for follow-up calls to get_artwork_details (full metadata) or get_artwork_image (deep-zoom viewer — only when the user asks to see, show, or view an artwork; do not open the viewer for list/count/summary requests).

Full metadata for ONE artwork by objectNumber: creator, dates, materials, provenance, inscriptions, related objects. Typically follows a search_artwork / semantic_search / find_similar result, or a user-named objectNumber. Provide exactly one of objectNumber (e.g. 'SK-C-5' for The Night Watch) or uri (a Linked Art URI from relatedObjects).

Returns metadata including titles (primary plus the full set of variants with language and qualifier — Dutch/English brief/full/display/former), creator, date, dateDisplay (free-text form), description, curatorial narrative, dimensions (text + structured: height/width/depth/weight/diameter where present), extentText, materials, object type, production details (with creator life dates, gender, and Wikidata ID where available), provenance, credit line, inscriptions, license, related objects (each carrying objectNumber + iiifId for in-viewer navigation), themes, exhibitions, attributionMarks (signature/inscription counts), externalIds (handle + other), location (museum room when on display, as { roomId, floor, roomName }), recordCreated/recordModified timestamps, plus collection sets and reference metadata. Authority IDs appear at two levels: work-level under externalIds (handle + other), and entity-level under equivalents[] arrays on objectTypes, materials, production entries, subjects.depictedPersons / subjects.depictedPlaces, collectionSetLabels and themes — each entry a { authority, id, uri } triple (VIAF/ULAN/RKD/Getty TGN+AAT/GeoNames/Wikidata), and one entity can carry several, so read every entry (iconclass terms have none). The relatedObjects field carries each peer's objectNumber (canonical handle) plus a Linked Art objectUri; pass either form back here, objectNumber preferred.

Not for filter-based discovery — use search_artwork. Not for similarity discovery — use find_similar. Not for aggregate counts — use collection_stats.

Scholarly references for ONE artwork by objectNumber: citations, with linked publication, pages, ISBN where known. Follows a search_artwork / get_artwork_details result. By default returns the first 5 plus a total count; set full=true for all entries (major works can have 100+ — mind the context window). Not for general metadata — use get_artwork_details. Not for library-catalogue search.

Reverse bibliography lookup: artworks whose references cite a given publication, by its URI or id. Use the publicationUri from get_artwork_bibliography (e.g. 'https://id.rijksmuseum.nl/301154354') or the bare id. Local and resolver-free. Not for topic search of the library catalogue.

Conservation/forensics record for ONE artwork: technical examinations and restoration treatment history. Follows get_artwork_details / a search result, by objectNumber. Returns technical examinations (X-ray, dendrochronology, paint samples, infrared), conservation/restoration treatment events, a count of recorded signature/inscription marks (use search_inscriptions for the actual transcriptions), and a short provenance excerpt. Not for general metadata — use get_artwork_details. Not for transcribed inscriptions — use search_inscriptions. Not for aggregate counts — use collection_stats.

Opens an interactive deep-zoom viewer for the user — only when they ask to see, show, or view an artwork. Call ONLY when the user explicitly wants to see, show, or view an artwork. Do NOT call for list, summary, count, or text-only requests. Not for visual analysis by the LLM — use inspect_artwork_image to get image bytes. Not all artworks have images available. Returns metadata and a viewer link, not the image bytes themselves; do not construct or fetch IIIF image URLs manually (downloadable images are on rijksmuseum.nl).

Internal: switch the viewer to a different artwork while preserving the viewUUID. Called by the artwork-viewer iframe during in-viewer related navigation. Any user highlight is cleared on remount because its coordinates belong to the previous artwork.

Returns image bytes (base64) for the LLM's own visual analysis of an artwork or region. The LLM can see and reason about the image immediately — not for the user to view (use get_artwork_image for the interactive viewer). Not for listing or summarising artworks — use search_artwork.

Use with region 'full' (default) to inspect the complete artwork, or specify a region to zoom into details, read inscriptions, or examine specific areas. The response includes cropPixelWidth/cropPixelHeight: the actual pixel dimensions of the returned image.

Region coordinates: 'pct:x,y,w,h' (percentage of full image, recommended), 'crop_pixels:x,y,w,h' (pixel coordinates of the full image — use with nativeWidth/nativeHeight from a prior response), or 'x,y,w,h' (legacy IIIF pixels, equivalent to crop_pixels). Quick reference:

• Top-left quarter: pct:0,0,50,50

• Bottom-right quarter: pct:50,50,50,50

• Center strip: pct:25,25,50,50

• Full image: full (default)

• For multi-panel works: use physical dimensions from get_artwork_details to estimate panel percentages, then inspect individual panels with close-up crops.

Iterative zoom: start with region 'full' to understand the layout, then use close-up crops (600–800px) to read specific features. When a viewer is open for this artwork, it automatically zooms to the inspected region (navigateViewer defaults to true, no effect when region is 'full'), keeping the viewer in sync with your analysis — no separate navigate_viewer call needed for basic zoom.

The response includes the active viewUUID (if any) for follow-up navigate_viewer calls.

Zooms/pans an already-open viewer to a region — steer the user's view to a detail. Requires a viewUUID from a prior get_artwork_image call (the viewer must be open). Not for opening the viewer — use get_artwork_image. Not for visual analysis — use inspect_artwork_image.

In most cases you do NOT need this tool: inspect_artwork_image already auto-zooms the open viewer to whatever region it inspects. Call navigate_viewer only to move the user's view WITHOUT fetching image bytes for your own analysis.

By default, region coordinates are in full-image space (percentages or pixels of the original image), not relative to the current viewport. The same pct:x,y,w,h used in inspect_artwork_image will target the identical area in the viewer. Exception: when a command includes relativeTo, region is interpreted in that inspected crop's local coordinate space.

Region formats:

• 'pct:x,y,w,h' — percentage of full image.

• 'crop_pixels:x,y,w,h' — pixel coordinates of the full image. Use nativeWidth/nativeHeight returned by inspect_artwork_image to bound values. When used with relativeTo + relativeToSize, crop_pixels is instead interpreted as pixels within that inspected crop.

• 'x,y,w,h' — equivalent to crop_pixels: (legacy IIIF form, kept for compatibility).

• 'full' | 'square' — whole image shortcuts.

Out-of-bounds regions are rejected with an overlay_region_out_of_bounds warning — correct the coordinates and retry. Keep batches under 10 commands per call. The viewer session (viewUUID) remains active for 30 minutes of idle inactivity — any polling or navigation resets the clock.

Coordinate shortcut: to zoom to a region of a prior inspect_artwork_image crop, use 'relativeTo' with the crop's region string and specify 'region' as coordinates within the crop's local space; the server projects to full-image space deterministically. Use pct:x,y,w,h for crop-local percentages, or crop_pixels:x,y,w,h plus relativeToSize:{width: cropPixelWidth, height: cropPixelHeight} from inspect_artwork_image for crop-local rendered pixels.

Response field deliveryState reports whether the iframe drained the commands immediately (delivered_recently), the iframe exists but hasn't polled recently and the commands are queued (queued_waiting_for_viewer — typical when scrolled out of view), or no iframe has connected yet (no_live_viewer_seen). In the queued case, the command is preserved server-side and will apply automatically when the viewer resumes polling — do not narrate this as a delivery failure to the user.

Internal: poll for pending viewer navigation commands

Browse thematic and sub-collection groupings curated by Rijksmuseum staff (drawings, paintings, iconographic sets). Each result carries memberCount, top dominantTypes, top dominantCenturies by membership, and a category heuristic (object_type / iconographic / album / sub_collection / umbrella) so you can pick the right scope. Use minMembers: 100, maxMembers: 200000 to avoid umbrella sets when the user wants a substantive subset. Pair with browse_set(setSpec) to enumerate members. Not for keyword search across artworks — use search_artwork. Not for aggregate counts — use collection_stats.

Enumerate the member artworks of one curated set by setSpec (from list_curated_sets). DB-backed (warm calls in tens of ms). Returns DB-direct records with objectNumber, title, creator, date (display + earliest/latest), description, dimensions, datestamp, image/IIIF URLs, and a stable lodUri. For multi-row vocab (subjects, materials, type taxonomy, full set memberships), follow up with get_artwork_details on the returned objectNumber. Supports pagination via resumptionToken (stateless base64; not portable across server upgrades). Not for set discovery — use list_curated_sets first.

OAI-PMH delta feed — records changed within a date range since a known harvest checkpoint, paginated. Use identifiersOnly=true for a lightweight listing (headers only, no full metadata). Each record includes an objectNumber for follow-up calls to get_artwork_details or get_artwork_image. Deleted records are flagged with deleted:true (marked [DELETED] in the listing) and carry only a LOD URI + datestamp, no metadata.