Get Board Context
get_board_contextRetrieves source-cited context from an ingested FigJam board snapshot, including section overviews, node excerpts, search results, and paginated details for summaries or documentation.
Instructions
Read source-cited context from an ingested board snapshot. Start overviews, summaries and documentation with a call without topic, nodeIds, limit and maxChars: its first page names the largest sections and lists sections with IDs. Then pass section, page, frame or group IDs as nodeIds; several IDs share each page in request order. For a whole-board summary, pass all top-level section IDs (at most 50 per call) with maxChars 24000, follow nextCursor, then read outsideSections: true. Default detail: "auto" switches reads of multiple distinct IDs or one page, section, frame or group to a compact overview only when the first full page would leave unread excerpts. Overview lines contain node IDs and deterministically shortened text (50–120 characters); structuredContent puts the excerpts once in overview.text, with empty evidence and clusters. limit applies only to the full view and is ignored in an overview, even when explicit. Read the complete source and Figma link with the same boardId and snapshotId, nodeIds: [""] and detail: "full"; table IDs read every row. Without overview, excerpts are in evidence. Read outsideSections: true, search with topic, or continue with cursor. Cite the node ID or Figma link behind each statement. Synthesize the answer yourself. No network or LLM calls; use ingest_board to refresh Figma content.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum evidence excerpts per full page (default 20, at most 100); ignored in an automatic overview, even when explicit. Use detail: full for an excerpt limit | |
| topic | No | Words to search for. An excerpt matches when at least one of them is in its text, its section or node name, the label of an arrow attached to it or, for a table row, its column headings, as a whole word ignoring case and accents (words of five or more letters also match compounds that begin with them); excerpts with more of the words come first. Other word forms, synonyms and translations do not match: include them yourself, for example "payment payments pay Bezahlung". Cannot be combined with nodeIds or outsideSections. | |
| cursor | No | nextCursor of the previous page, unchanged; send it with the same topic, nodeIds, outsideSections, detail, limit and maxChars | |
| detail | No | auto uses a compact, source-marked overview when a requested container or several nodeIds need multiple full pages; full returns linked evidence objects. Overview lines may be shortened; use full to read all text | auto |
| boardId | Yes | The Figma file key returned by ingest_board, or the board URL. A URL with a node-id, without nodeIds, topic and outsideSections, reads that node | |
| nodeIds | No | Read exact source nodes, all rows of a table or the row of a table cell, or every excerpt inside a page, section, frame or group by its ID (nested sections included, in reading order); several IDs in one call share every page in request order; cannot be combined with topic | |
| maxChars | No | Character budget for each representation: the readable text content and the JSON of structuredContent (default 12000, minimum 2000) | |
| snapshotId | No | Read a specific retained snapshot instead of the latest board | |
| outsideSections | No | Read every excerpt that lies in no section, cluster by cluster in reading order, tables row by row; on a board without sections, all excerpts. Cannot be combined with topic or nodeIds |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| clusters | Yes | ||
| evidence | Yes | Full linked excerpts; empty in overview mode, where excerpts are in overview.text instead | |
| overview | No | Present only for automatic compact overview pages; evidence and clusters are empty, not a claim of no matches. Read a line's full text and Figma link with the same boardId and snapshotId, its nodeId, and detail: full | |
| relations | No | Cluster-to-cluster relations derived from connector arrows | |
| truncated | Yes | ||
| nextCursor | No | ||
| snapshotId | Yes | ||
| truncation | Yes | Explicit omissions from structured results and the readable text | |
| connections | Yes | Arrows with at least one end, or a section, frame or group around one, among this page's excerpts; never arrows to a page. The label is the text on the arrow | |
| contextText | Yes | Orientation and reading instructions. Excerpts are in overview.text when overview is present (evidence and clusters are then empty), otherwise in evidence; text content carries the same readable excerpts | |
| totalMatched | Yes | ||
| unknownNodeIds | No | Requested nodeIds that are not in this snapshot; the others are read | |
| ignoredArguments | No | Unknown input keys that were ignored; their values are not echoed. Absent when none |