One component, whole
research_componentThe component a hit points at (uuid or event id): every event with its summary and structured fields, the evidence behind the quality tier, links to the Library of Congress page PDFs and to snewpapers.com (1 token). include_text=true adds the full text: 3 tokens, charged once per component - be selective, never page through full texts. component_id is a uuid or {uuid}_evt_N; the response echoes the requested event index so a client can highlight it. Caution components return only a description and links while guarded=true; for research the better experience is guarded=false - ask the researcher once, at the start of the session, then pass it on every call. If your own content rules cannot handle such historical text, do not fetch unguarded - give the researcher the site link. include_boxes=true (free) adds the component's rectangles per page as fractions of the page image, for drawing it.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"component_id": "<component_id>"
},
"name": "research_component"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| guarded | No | ||
| component_id | Yes | ||
| include_text | No | ||
| include_boxes | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | ||
| lccn | Yes | ||
| uuid | Yes | ||
| year | Yes | ||
| boxes | No | Only with include_boxes=true: rectangles per page as fractions of the page image (a cross-page story has an entry per page; a story in two columns has two rectangles on that page); null otherwise | |
| label | Yes | ||
| links | Yes | ||
| pages | No | ||
| state | No | ||
| county | No | A title can span several (LoC data) | |
| events | Yes | ||
| thumbs | No | null until the thumbnail stage is re-wired for the new pipeline | |
| caution | No | ||
| content | No | Full text (tables spliced in), only with include_text=true; withheld for caution components under guarded=true | |
| citation | Yes | Cite from this; the same with or without text | |
| evidence | Yes | ||
| resolved | No | false: the extractor judged it incomplete — a lost opening, or continued in a later issue | |
| newspaper | Yes | ||
| char_count | No | ||
| issue_date | Yes | ||
| issue_uuid | Yes | ||
| event_count | Yes | ||
| issue_pages | No | Page count of the whole issue (this component's own pages are `pages`); null when the issue has no page images recorded | |
| embed_worthy | No | ||
| quality_tier | Yes | ||
| chain_members | No | >= 2: merged across pages; the evidence below is the WORST case over the fragments | |
| tokens_charged | Yes | What this call cost (full text: 3 once per component, then 0) | |
| quality_tier_why | No | The first condition that decided a non-green tier (e.g. fuzz_lt_92, lt80_gt_0.05); "green" for green | |
| tokens_remaining | Yes | Your balance after it | |
| caution_description | No | ||
| requested_event_idx | No | Echo of the event in the id you asked with |