Skip to main content
Glama

USVI Public Records: Newspapers

Search the Danish West Indies papers

search_danish_papers
Read-onlyIdempotent

Search the Danish West Indies newspapers, 1770–1885, page by page, as the Royal Danish Library (Mediestream) holds them: Sanct Thomæ Tidende, the Danish-era St. Croix Avis, the St. Thomas Herald and the Saint Croix Bulletin. OPENED, NOT PRESERVED: the library keeps these papers; this archive made them searchable and links every page to the library's copy. A separate collection from this server's other papers, read only by this tool. words="danish" (the default) searches your words as typed, with Danish letters folded (æ→ae, ø→o, å→a), because the library's OCR has none, and on pages before 1816 also the long-s spelling (an s printed like an f and read as f). words="english" turns your English words into the Danish forms the papers printed, from a word list made by machine and not yet checked by a reader of Danish; every answer names each Danish form searched, and the English word is searched too, since some papers and notices are English. Nothing is translated. The OCR is poor (by the library's own estimates about half the characters on a typical page are misread), so search finds what scanned well and misses a great deal; we are working to improve it. Each result is one page: paper, date, page, the library's estimate of its OCR quality, a short snippet labeled uncorrected OCR (not fit to quote), and the library's page link to read and check. Hit counts are pages, never articles. An empty result is not evidence that the papers never printed 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": {
      "query": "<query>"
    },
    "name": "search_danish_papers"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoResults page, 20 pages of the papers per results page. Default 1.
paperNo"Sanct Thomæ Tidende", "St. Croix Avis", "St. Thomas Herald", "Saint Croix Bulletin", or a slug. Leave out for all four.
queryYesNames, places, ships, streets or words. Quote a phrase to require it intact. Danish letters may be typed or not.
wordsNo"danish" (default): search the words as typed. "english": search English words through the Danish word list.
long_sNoDefault true: also search the long-s spelling on pages before 1816. false turns it off.
date_toNoLatest date, same forms; a year includes all of it.
date_fromNoEarliest date: a year (1848) or a day (1848-07-03), within 1770–1885.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent annotations, it discloses that the library preserves the originals while this archive only links, that OCR is roughly half misread, that snippets are uncorrected OCR 'not fit to quote', and that hit counts are pages, never articles. It also warns that the English word list is machine-made and unchecked by a Danish reader. These are exactly the behavioral traits an agent needs and cannot get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and scope are front-loaded, followed by search-mode behavior and then the accuracy caveats, which is a sensible order. It is dense and occasionally emphatic ('OPENED, NOT PRESERVED', 'not fit to quote'), but nearly every sentence conveys information an agent needs. Slightly longer than strictly necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the return-value burden and does so fully: each result is one page with paper, date, page, the library's OCR-quality estimate, a labeled snippet, and the library's page link, with the clarification that counts are pages not articles. Combined with the OCR caveat, this is complete for a 7-parameter search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: Danish letters are folded (æ→ae, ø→o, å→a), long-s spelling is searched before 1816 and can be turned off, the English mapping is unverified and every answer names the Danish forms searched, and page results are 20 pages each. It does not add much on date_from/date_to beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Search the Danish West Indies newspapers, 1770–1885, page by page') and names the four titles covered. It explicitly separates this collection from the server's other papers ('A separate collection from this server's other papers, read only by this tool'), so an agent can route to it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete when-to guidance: use words="danish" for words as typed, words="english" to map English terms through the Danish word list, and omit paper to cover all four titles. It also sets expectations that an empty result is not evidence of absence. It stops short of naming sibling tools like search_newspapers or list_papers, so routing to alternatives is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources