Search LOC digital collections, Chronicling America newspapers (full OCR), and LC Subject Headings.
Scored across 6 tools
Each tool targets a distinct resource and action: browse_collections for curated collections, search_items for item discovery, search_newspapers for Chronicling America pages, search_subjects for LCSH headings, get_item for item metadata, and get_newspaper_page for page text. The descriptions explicitly cross-reference each other and clarify boundaries (e.g., is_item true/false, when to use search_newspapers vs search_items). No two tools appear to do the same thing.
All six tools share the same libofcongress_ prefix and follow a strict verb_noun convention: browse_collections, get_item, get_newspaper_page, search_items, search_newspapers, search_subjects. There are no deviations or mixed conventions.
Six tools is well-scoped for a read-only digital library API. Each tool covers a distinct facet (collections, items, newspapers, subjects, page text) with no redundancy, and the count is comfortably within the ideal 3-15 range.
The surface covers discovery, metadata retrieval, page-level text access, and subject vocabulary for a read-only LOC API, which is strong. Minor gaps exist, such as a direct tool to fetch a single collection's full metadata or to list all items in a collection without going through search, but agents can work around these via search filters and returned URLs.
List and browse Library of Congress curated digital collections. Returns collection names, descriptions, item counts, slugs, and URLs. Optionally filter by keyword. Collections are curated subsets of the digital holdings with specific focuses (e.g., "Civil War Glass Negatives", "Baseball Cards", "WPA Posters"). Use the returned URL to navigate directly to a collection on loc.gov.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | 1-indexed page number for paginating results. | |
| limit | No | Maximum number of collections to return. Default 25. A page holds at most 100 collections: a larger limit (up to 1000) is served as a 100-collection page, and page then counts 100-collection pages. | |
| query | No | Optional keyword to filter collections by name or description. Omit to list all collections. |
| Name | Required | Description |
|---|---|---|
| page | No | Current 1-indexed page number. |
| error | No | Present when the call failed. Absent on success. |
| pages | No | Total number of pages available. |
| total | No | Total number of matching collections across all pages. |
| notice | No | Recovery hint when results are empty or a page is out of range — suggests broadening the keyword or removing filters — plus disclosure of a capped limit. Absent on ordinary result pages. |
| has_next | No | True when more pages are available after this one. |
| totalCount | No | Total matching collections — mirrors output.total for agent reasoning. |
| collections | No | LOC curated collections matching the keyword filter, or all collections when no keyword is specified. |
| effectiveLimit | No | The page size actually served when limit exceeded the per-call cap of 100. Absent when limit was within the cap. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the description's main added value is the output shape and the URL navigation behavior. It does not mention pagination behavior beyond what the schema says or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the action and resource, then return fields, filtering, and navigation in logical order. Five sentences is slightly more than needed but each adds some value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema exists so return values needn't be detailed, and the description covers purpose, filtering, and URL navigation. Minor gap is the absence of explicit sibling routing guidance, but overall adequate for a simple read-only listing tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are fully documented; the description only reinforces the optional keyword filter. Baseline 3 applies since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (list/browse) and resource (LOC curated digital collections), and distinguishes it from search_items/search_newspapers siblings since this enumerates collections rather than items. The clarification that collections are curated subsets with examples makes the resource concrete.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explains how to filter optionally and that the returned URL navigates to loc.gov, but never explicitly states when to use this vs search_items or search_subjects. The sibling differentiation is implied by resource type, not spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the full metadata record for a specific LOC digital item. Returns the imprint (place, publisher, and date of publication), contributors, LCSH subject headings and the subject terms the search subject filter accepts, summary, languages, locations, rights information, physical description, call number, original and online formats, access restrictions, former catalog IDs, notes, and related items, plus the item's digital resources (each with its page count, representative image, PDF, and audio) and a window of its pages. Each page has a page_url and has_text; pass a page_url with has_text true to libofcongress_get_newspaper_page to read that page's text (newspaper, book, and manuscript pages alike). A long item lists 50 pages per call: continue with page_offset set to next_page_offset. Set include_files for each listed page's downloadable files (TIFF, JP2, JPEG sizes, text). Use after libofcongress_search_items on a result whose is_item is true. Pass the result id — a simple ID, an LCCN, or a slash-separated newspaper path — or a loc.gov item link (https://www.loc.gov/item/<id>/) or LCCN permalink (https://lccn.loc.gov/<lccn>), which is read as its id. Non-item results (is_item: false) — collections, exhibits, guides, newspaper pages, catalog.loc.gov records, hdl.loc.gov finding aids — have no item record and cannot be retrieved here.
| Name | Required | Description | Default |
|---|---|---|---|
| item_id | Yes | LOC item id from a libofcongress_search_items result's "id" field (where is_item is true): a simple ID ("2009632251", "2005691065") or a slash-separated path for newspaper issues ("sn95047246/1935-09-05/ed-1"). A loc.gov item link is also read as its id: "https://www.loc.gov/item/2009632251/", http or without "www.", or "item/2009632251"; so is an LCCN permalink, as its normalized LCCN: "https://lccn.loc.gov/2005567251", http or without a scheme; "lccn.loc.gov/2005-568294" reads as 2005568294. Any other URL, such as a /resource/ page URL, is rejected. | |
| page_limit | No | Pages to list. Default 50. A response lists at most 100 pages: a larger page_limit (up to 1000) is served as 100. | |
| page_offset | No | Index of the first page to list, 0-based across all of the item's resources. Default 0. Pass next_page_offset from the previous response to continue. | |
| include_files | No | Also list the download URLs of each listed page's files — every JPEG size, the JP2 and TIFF masters, OCR XML, and text files. Default false. |
| Name | Required | Description |
|---|---|---|
| url | No | Canonical LOC item URL. |
| date | No | Publication or creation date as LOC catalogs it: free text, a year, or a full date (e.g., "1936 Apr.", "1909-1911.", "1894", "1912-04-16"). Absent when LOC records only a coded value ("uuuu", "||||") or none. |
| error | No | Present when the call failed. Absent on success. |
| notes | No | Descriptive notes and annotations from catalogers. |
| pages | No | The window of the item's pages starting at page_offset, across every resource in order. Empty when the item has no pages or page_offset is past the last page. |
| title | No | Item title. |
| notice | No | Set when page_offset is past the last page, or when page_limit was capped. Absent otherwise. |
| imprint | No | Imprint as LOC catalogs it: place, publisher, and date of publication (e.g., "New York : Werner School Book Company, c1900."), or a date alone on many photos and manuscripts ("1936 Apr."). Absent when LOC records none. |
| item_id | No | LOC item ID: the input item_id, or the id read from the loc.gov item link or LCCN permalink passed as item_id. |
| summary | No | Cataloger's abstract of the item's subject and historical context. |
| languages | No | Languages of the item (e.g., "english"). |
| locations | No | Places the item depicts or originates from (e.g., "united states"). |
| resources | No | The item's digital resources, in LOC order. Empty when no digital surrogate exists. |
| former_ids | No | Superseded catalog identifiers or URLs this item was previously known by. |
| page_total | No | Pages across all of the item's resources. |
| totalCount | No | Pages across all resources — mirrors output.page_total for agent reasoning. |
| call_number | No | LOC call number — the shelf location for requesting the physical original. |
| contributors | No | Contributors, creators, or photographers as LOC catalogs them, role included (e.g., "Washington, George, 1732-1799 (Author)"). One person can appear once per role. Empty when LOC lists none. |
| related_items | No | IDs or URLs of related LOC records for follow-up retrieval; a title stands in for a related record LOC gives neither for. |
| subject_terms | No | Subject terms LOC indexes this item under: lowercase heading components without dates (e.g., "civil war", "united states"). Each is a value the libofcongress_search_items subject filter accepts. |
| online_formats | No | Formats the digitized surrogate is available in (e.g., "image"). |
| next_page_offset | No | page_offset for the next window of pages. Absent when this window reaches the last page. |
| original_formats | No | Material types of the original (e.g., "photo, print, drawing"). |
| subject_headings | No | Library of Congress Subject Headings (LCSH) assigned to this item, as cataloged (e.g., "United States--History--Civil War, 1861-1865"). Empty when the record carries none. |
| access_restricted | No | True when LOC restricts access to the original. Absent when upstream omits it. |
| effectivePageLimit | No | The page_limit actually served when page_limit exceeded the per-call cap of 100. Absent when page_limit was within the cap. |
| rights_information | No | Rights and reproduction statement for this item. |
| physical_description | No | Physical or technical description of the original item. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely new behavioral facts: a 50-page window per call, continuation via next_page_offset, the 100-page response cap regardless of page_limit, and the failure mode for non-item IDs. This is well beyond what the annotations provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the core purpose, then pagination mechanics, then the alternative tool, then exclusions. It is on the long side and the enumeration of returned fields partially duplicates the output schema, but nearly every sentence carries actionable information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given an output schema exists, the return-field inventory is optional, yet the description still covers the two things an agent most needs to call correctly: pagination continuation and which IDs are valid vs. invalid. Nothing needed for correct invocation is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the schema itself already documents the accepted ID formats (simple ID, newspaper path, loc.gov link, LCCN permalink) and the page_offset continuation contract, so the description largely restates it. It adds the useful framing that page_url + has_text can be handed to the newspaper-page tool, but that is response-side rather than parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (retrieve) and resource (full metadata record for a specific LOC digital item), and names the exact precondition that identifies valid inputs (is_item: true) while distinguishing itself from libofcongress_search_items and libofcongress_get_newspaper_page.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says to use it after libofcongress_search_items on a result whose is_item is true, and enumerates the cases where it must NOT be used (collections, exhibits, guides, newspaper pages, catalog.loc.gov, hdl.loc.gov finding aids). It also routes the agent onward to libofcongress_get_newspaper_page with a concrete condition.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the full text of one LOC page — a historical newspaper page, or a book or manuscript page — or, with match, only the passages around your search terms, with its publication metadata: for newspapers the title, issue date, place of publication, indexed states, and edition; for every page its sequence, the page count, and the item_title and item_id of the issue, book, or manuscript it belongs to — pass item_id to libofcongress_get_item to list every page of the item. Pass the url field from a libofcongress_search_newspapers result, or a pages[].page_url from libofcongress_get_item (has_text true), or a Chronicling America page link (…/ed-N/seq-M/) — do not construct this URL manually. A dense newspaper page runs to 50,000 characters: to find the article a search hit on, pass the search query as match and read the passages around it rather than the whole page. The text is OCR, or for some manuscripts a volunteer transcription; OCR quality varies by digitization batch and era, and 19th-century and degraded materials may contain fragmented text, garbled words, and line-break artifacts that are surfaced as-is. When a page exists but has no digitized text, ocr_available is false and ocr_text is empty — this is a data property, not an error.
| Name | Required | Description | Default |
|---|---|---|---|
| match | No | Return the passages around these terms instead of the whole page — pass the query you gave libofcongress_search_newspapers (e.g., titanic, or "the titanic" iceberg); the q= in a search result url is not read as match. Words separated by spaces are separate terms, any of which matches; a double-quoted span is one phrase. Each matches case-insensitively as literal text, with line breaks read as spaces; OCR misreads are not repaired. When set, ocr_text is empty, matches holds up to 10 passages of about 300 characters either side of each occurrence — when they need more, occurrences of the rarest terms come first, so a common word only fills the slots left — and match_count counts every occurrence. Omit match for the whole page. Up to 200 characters; blank is ignored. | |
| page_url | Yes | A LOC page URL: the url field from a libofcongress_search_newspapers result (e.g., "https://www.loc.gov/resource/sn83045462/1905-03-15/ed-1/?sp=1"), or a pages[].page_url from libofcongress_get_item for a newspaper, book, or manuscript page (e.g., "https://www.loc.gov/resource/mss93930.mss93930-001/?sp=3"). Also accepted: the same /resource/ URL over http or without "www.", a newspaper page path ending /ed-N/seq-M/, and a Chronicling America page link (`chroniclingamerica.loc.gov/lccn/<lccn>/<date>/ed-N/seq-M/`); each is read as its https://www.loc.gov/resource/…/?sp=M page. Pass the value as returned — do not construct page URLs. |
| Name | Required | Description |
|---|---|---|
| date | No | Issue publication date (YYYY-MM-DD). |
| error | No | Present when the call failed. Absent on success. |
| notice | No | Set when ocr_available is true but the page's text came back empty, saying why: the text service did not answer this call (retry), its answer could not be read as text (retrying will not help), or the page's text is empty — a blank page, including one LOC sends as the placeholder [NO TEXT AVAILABLE FOR THIS PAGE]. Distinguishes these from a genuinely image-only page (where ocr_available is false), which carries no notice. With match set on a page that has text, set instead when nothing matched or when some occurrences fall outside the passages returned — those are read on the whole page, by calling again without match. Absent otherwise. |
| states | No | Every US state LOC indexes this newspaper title under (e.g., ["georgia", "south carolina"]), in LOC order — possibly more than the state of publication. Absent when LOC lists no state. |
| edition | No | Edition number of the issue (e.g., "1"). Absent when LOC gives none. |
| item_id | No | ID of the item this page belongs to: the newspaper issue (e.g., "sn83030214/1912-04-16/ed-1"), book, or manuscript volume (e.g., "mm77093930"). Pass it to libofcongress_get_item to list every page of the item, each with its page_url and has_text — for an article continued on a later page, or the next page of a book. Absent when LOC names no item. |
| matches | No | Present only when match is set: passages of the page text around the occurrences of the match terms, in page order — about 300 characters either side of each occurrence, overlapping passages merged up to 1,200 characters, never overlapping, at most 10, chosen around the rarest terms first when more would be needed. Empty when nothing matched or the page has no text. |
| ocr_text | No | Full plain text of this page: OCR, or for some manuscripts a volunteer transcription. Empty string when match is set (read matches instead), when ocr_available is false, or when the page is blank or its text could not be retrieved (see notice). May contain fragmented words, line-break artifacts, and misspellings inherent to historical OCR — do not attempt to repair. |
| page_url | No | The LOC resource URL for this page, in the https://www.loc.gov/resource/…?sp=N form the input was read as. |
| sequence | No | Page sequence number within the issue, volume, or folder. |
| item_title | No | Title of the item this page belongs to, on every page type: the book or manuscript title, or for a newspaper page the issue title with place and date (e.g., "New-York tribune (New York [N.Y.]), April 16, 1912"). Absent when LOC gives none. |
| match_count | No | Present only when match is set: occurrences of every match term on the page, including those beyond the passages returned. 0 when nothing matched or the page has no text. |
| ocr_available | No | True when LOC lists OCR or transcribed text for this page, even if the text it returns is empty (see notice). False for image-only pages where no text has been produced. |
| segment_count | No | Number of pages in the issue, volume, or folder. Absent when LOC gives none. |
| newspaper_title | No | Title of the newspaper publication. Absent when LOC gives none. |
| place_of_publication | No | Where the newspaper was published, as LOC catalogs it (e.g., "Charleston, S.C."). Absent when LOC gives none. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint/openWorldHint annotations, the description discloses the 50,000-character page size and the match workaround, that text is OCR or volunteer transcription with batch-/era-dependent quality artifacts, and crucially that ocr_available=false with empty ocr_text is a data property rather than an error. These are exactly the failure modes an agent would otherwise misread.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose is front-loaded and nearly every clause carries information (metadata fields, URL sources, OCR caveats), so little is filler. It is, however, a single very dense em-dash chain that is harder to parse than a two- or three-sentence split would be, and the 'do not construct this URL manually' point is stated twice.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite an output schema existing (so return values need not be explained), the description still maps the metadata an agent will get and covers the edge cases that matter: empty-but-valid pages, OCR degradation, and match truncation to ~300-char passages with match_count. Nothing needed to call it correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and both parameters already carry rich inline docs, including the page_url source forms and the match passage mechanics. The description's parameter guidance largely restates the schema (URL sourcing, don't construct manually), adding little that isn't already structured. Baseline 3 applies when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (retrieve) and resource (one LOC page), and immediately delimits variants: a newspaper/page vs. book/manuscript page, and full text vs. match passages. It also names the sibling tools it works alongside (libofcongress_search_newspapers, libofcongress_get_item), so an agent can place it precisely in the family.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit routing is given: pass page_url from a search_newspapers result or a pages[].page_url from get_item, use match for pinpointing an article on a dense page, and omit it for the whole page. It also states the negative case ('do not construct this URL manually') and points to libofcongress_get_item for listing an item's pages.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Library of Congress digital collections by keyword. Optionally filter by material format (photos, maps, newspapers, audio, etc.), date range, subject heading, or geographic location, or scope the search to a single curated collection with collection_slug. Returns item summaries with titles, dates, descriptions, LOC IDs, and format tags. Each result carries is_item: pass the id of a result where is_item is true to libofcongress_get_item for full metadata; results where is_item is false are non-item resources (collections, exhibit and research-guide pages, newspaper-page results, catalog.loc.gov records, hdl.loc.gov finding aids) with no item record — open their url instead. Use libofcongress_search_subjects to find an LCSH heading for the subject filter. To discover the subject and location values the filters accept for a search, set include_facets to get its top subject_facets and location_facets.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | 1-indexed page number for paginating results. | |
| limit | No | Results per page. Default 25. A page holds at most 100 results: a larger limit (up to 1000) is served as a 100-result page, and page then counts 100-result pages. | |
| query | Yes | Full-text search across metadata and available descriptive text. | |
| format | No | Material type filter. Options: photo, map, newspaper, manuscript, audio, film, book, notated-music. Omit to search all formats. | |
| subject | No | Subject filter: an LCSH heading from libofcongress_search_subjects (e.g., "World War, 1939-1945", "United States--History--Civil War, 1861-1865") or a subject term from subject_facets (include_facets) or libofcongress_get_item subject_terms (e.g., "world war"). LOC indexes headings by their parts, so the value is split at "--" into lowercase terms with dates dropped, and an item must carry every term. | |
| date_end | No | End year for date filter, inclusive (e.g., 1930). Omit to run through the current year. | |
| location | No | Geographic location filter (e.g., "oklahoma", "washington d.c."). Lowercase, matches LOC location facets; location_facets (include_facets) lists values for a search. | |
| date_start | No | Start year for date filter, inclusive (e.g., 1920). Omit for no lower bound. | |
| include_facets | No | Also return subject_facets and location_facets: LOC's top subject and location terms across every match, with counts — the values the subject and location filters accept. Default false: facets add time to each search, so request them when you need filter values to narrow by. | |
| collection_slug | No | Scope the search to one curated collection. Use a slug exactly as returned by libofcongress_browse_collections (e.g., "aaron-copland") — slugs are not derivable from the collection title. Cannot be combined with format; omit format and read each result's format field instead. Omit to search all of LOC. |
| Name | Required | Description |
|---|---|---|
| page | No | Current 1-indexed page number. |
| error | No | Present when the call failed. Absent on success. |
| items | No | Item summaries matching the search query and filters. |
| pages | No | Total retrievable pages. For result sets larger than LOC will page through (~100,000 items) this is capped, and a notice discloses how to reach the rest (partition by date/subject/location). |
| total | No | Total number of matching items across all pages. |
| notice | No | Recovery hint when results are empty or a page is out of range — echoes applied filters, subject terms and location included, and suggests how to broaden — plus disclosure of a capped limit or of the retrieval ceiling. Absent on ordinary result pages. |
| has_next | No | True when a retrievable next page follows this one. Never promises a page past LOC's ~100,000-item retrieval ceiling. |
| totalCount | No | Total matching items across all pages — mirrors output.total for agent reasoning. |
| effectiveLimit | No | The page size actually served when limit exceeded the per-call cap of 100. Absent when limit was within the cap. |
| effectiveQuery | No | The query as submitted to the LOC API, after trimming. |
| subject_facets | No | LOC's top subject terms across every item matching this search (up to 10), most frequent first. Pass a value as the subject filter to narrow the search. Present only when include_facets is true; empty when LOC reports none. |
| location_facets | No | LOC's top location terms across every item matching this search (up to 10), most frequent first. Pass a value as the location filter to narrow the search. Present only when include_facets is true; empty when LOC reports none. |
| effectiveSubjectTerms | No | The subject terms the subject filter was sent as, all required to match. Absent when no subject filter was given. |
| effectiveCollectionSlug | No | The collection the search was scoped to, after trimming. Absent when the search covered all of LOC. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare only readOnlyHint and openWorldHint; the description goes well beyond them by disclosing the is_item routing contract, the concrete non-item resource types (collections, exhibit/research-guide pages, newspaper pages, catalog.loc.gov records, hdl.loc.gov finding aids), and the cost tradeoff that facets add time to each search.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose and primary filters are front-loaded, then routing rules and facet guidance follow in a logical order with no filler. The long parenthetical enumerating non-item resource types is dense but earns its place by telling the agent what to do with those results.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 10-parameter, mixed-result search tool with an output schema already present, the description covers everything an agent needs to act: filter sourcing, facet discovery, the collection_slug/format conflict, and how to dispatch each result type. Return-value shape is left to the output schema, which is correct.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 semantics the schema does not: the subject value is split at "--" into lowercase terms with dates dropped and an item must carry every term, and collection_slug must be a slug from libofcongress_browse_collections because it is not derivable from a title. It stops short of explaining limit/page interaction, which the schema already handles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Opens with a specific verb+resource pair ("Search the Library of Congress digital collections by keyword") and immediately enumerates the filter axes available. It explicitly names the sibling tools it routes to (libofcongress_get_item, libofcongress_search_subjects) and distinguishes itself from them, so an agent can place it without opening a schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit when-to-use routing: pass is_item=true ids to libofcongress_get_item, open url for is_item=false resources, use libofcongress_search_subjects to source an LCSH heading, and set include_facets to discover subject/location filter values. It also states a hard exclusion — collection_slug cannot be combined with format — which is exactly the kind of constraint that prevents a failed call.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search historical newspaper pages in the Chronicling America corpus. Returns matching pages with the opening of each page's OCR text (~500 characters), publication title, date, the states LOC indexes the title under, and the page URL needed for libofcongress_get_newspaper_page. Filters by keyword, date range, US state, and newspaper title. The excerpt is the page's first lines, not the text around the match: to read where the query occurs, call libofcongress_get_newspaper_page with the returned url field and this query as its match, which returns the passages around each occurrence; omit match for the full page text. OCR quality varies: 19th-century and degraded materials may contain fragmented or garbled text.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | 1-indexed page number for paginating results. | |
| limit | No | Results per page. Default 25. A page holds at most 100 results: a larger limit (up to 1000) is served as a 100-result page, and page then counts 100-result pages. | |
| query | Yes | Keyword search across OCR text and newspaper metadata. | |
| state | No | Filter to newspapers LOC indexes under this US state: the full state name (e.g., "oklahoma", "new york") or its two-letter postal code (e.g., "OK", "NY"), case-insensitive. Use "district of columbia" (or "DC") for Washington, D.C.; "washington" means Washington state. City and county names match nothing. | |
| date_end | No | End of the date filter, inclusive, in the same forms as date_start (e.g., 1920 or "1912-04-16"). A year or month ends on its last day, so "1912-04" runs through April 30. Omit to run through the current year. | |
| date_start | No | Start of the date filter, inclusive: an integer year (e.g., 1900) or a "YYYY", "YYYY-MM", or "YYYY-MM-DD" string (e.g., "1912-04-15"); month and day may be one or two digits. A year or month starts on its first day. Omit for no lower bound. | |
| newspaper_title | No | Filter to one newspaper. Pass the newspaper_title value of a libofcongress_search_newspapers result exactly (case-insensitive), e.g., "new-york tribune (new york [n.y.]) 1866-1924" — the full catalog title with place and run. A shortened title such as "New-York Tribune" matches nothing. |
| Name | Required | Description |
|---|---|---|
| page | No | Current 1-indexed page number. |
| error | No | Present when the call failed. Absent on success. |
| items | No | Newspaper page results matching the search query and filters. |
| pages | No | Total retrievable pages. For result sets larger than LOC will page through (~100,000 pages) this is capped, and a notice discloses how to reach the rest (partition by date/state). |
| total | No | Total number of matching newspaper pages in the result set. |
| notice | No | Recovery hint when results are empty or a page is out of range — echoes applied filters and suggests how to broaden — plus disclosure of a capped limit or of the retrieval ceiling. Absent on ordinary result pages. |
| has_next | No | True when a retrievable next page follows this one. Never promises a page past LOC's ~100,000-item retrieval ceiling. |
| totalCount | No | Total matching newspaper pages — mirrors output.total for agent reasoning. |
| effectiveLimit | No | The page size actually served when limit exceeded the per-call cap of 100. Absent when limit was within the cap. |
| effectiveQuery | No | The keyword query as submitted to the Chronicling America API, after trimming. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover only readOnlyHint and openWorldHint, and the description adds substantially more: it enumerates the returned fields, warns that the ~500-char excerpt is the page opening rather than text around the match, and flags that 19th-century/degraded OCR may be fragmented or garbled. These are behavioral traits an agent cannot derive from the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with purpose and returns before the routing advice and the OCR caveat, and each sentence carries distinct information. It runs long at roughly five sentences, but nothing is redundant with the structured fields except the brief filter enumeration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite an output schema existing, the description supplies the practical context an agent needs: what the excerpt actually is, how to follow up for in-context text, and the OCR reliability caveat. Filtering, pagination, and return shape are all accounted for across description, schema, and output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so every parameter (state matching rules, date forms, exact newspaper_title, page/limit pagination) is already fully documented in the schema. The description only restates that filtering exists by keyword, date range, state, and title, adding no syntax or edge-case detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (Search) and resource (historical newspaper pages in the Chronicling America corpus), and explicitly distinguishes itself from libofcongress_get_newspaper_page by naming that sibling and its role. An agent can tell it apart from the other search/browse siblings without opening a schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit routing: use libofcongress_get_newspaper_page with the returned url field and the same query as match to see passages around the hit, or omit match for full page text. It also explains why this tool's excerpt is insufficient for that purpose, so the when-to-use-this vs. when-to-use-the-alternative decision is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Library of Congress Subject Headings (LCSH) by keyword. Returns authorized subject headings and their URIs, ranked by relevance with a heading that exactly matches the query first; a partial word with no keyword match returns the headings that begin with it. Use the returned label as the subject filter in libofcongress_search_items — LCSH uses precise, standardized terms that differ from natural language (e.g., "World War, 1939-1945" not "World War II"; "Aerial photography" not "Photography, Aerial"). Running this tool before a subject-filtered libofcongress_search_items dramatically improves result quality.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of subject headings to return. Default 10. A call returns at most 50 headings; a larger limit (up to 1000) returns up to 50. | |
| query | Yes | Keyword or partial subject heading to search for (e.g., "civil war", "immigration", "jazz"). |
| Name | Required | Description |
|---|---|---|
| cap | No | The heading limit applied to this response. |
| error | No | Present when the call failed. Absent on success. |
| shown | No | Number of subject headings returned in this response. |
| total | No | Number of subject headings returned. |
| notice | No | Recovery hint when no heading matched; how many headings matched when more exist than this response holds; disclosure of a capped limit. Absent when every matching heading was returned. |
| subjects | No | LCSH subject headings matching the query, ordered by relevance, an exact match first. To see how many LOC items carry a heading, pass its label as the libofcongress_search_items subject filter and read total. |
| truncated | No | True when more headings match than this response holds. Refine the query to see others, or raise limit when it is below 50. |
| effectiveLimit | No | The heading count actually applied when limit exceeded the per-call cap of 50. Absent when limit was within the cap. |
| effectiveQuery | No | The query as submitted to the id.loc.gov subject suggest endpoint, after trimming. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description goes further than the structured data by disclosing ranking behavior (exact match first), fallback behavior for partial words, and the shape of the result (headings plus URIs). It omits any note on the 50-result cap, but that ceiling is carried in the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with purpose, then ranking behavior, then the cross-tool workflow. Dense and mostly waste-free, though the closing sentence about improving result quality partly restates the earlier instruction to use the label as a filter.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter lookup tool with an output schema, an explicit safety annotation set, and a fully described schema, the description supplies everything an agent needs: what it returns, how results are ordered, and how they feed a sibling tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both parameters are already documented in the schema, including the limit cap and the query semantics. The description reinforces query intent with example terms but adds no syntax or format detail beyond what the schema provides, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Search Library of Congress Subject Headings (LCSH) by keyword') and immediately characterizes the return (authorized headings and URIs). An agent can distinguish it from libofcongress_search_items, which searches items rather than the heading vocabulary.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells the agent to run this before a subject-filtered libofcongress_search_items and to feed the returned label in as the subject filter. It names the alternative tool and the condition that selects it, leaving nothing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
libofcongress_get_item6 fields changedInput schema / properties / item_id / descriptionPrevious value: -"LOC item id from a libofcongress_search_items result's \"id\" field (where is_item is true): a simple ID (\"2009632251\", \"2005691065\") or a slash-separated path for newspaper issues (\"sn95047246/1935-09-05/ed-1\"). A loc.gov item link is also read as its id: \"https://www.loc.gov/item/2009632251/\", http or without \"www.\", or \"item/2009632251\". Any other URL, such as a /resource/ page URL, is rejected."New value: +"LOC item id from a libofcongress_search_items result's \"id\" field (where is_item is true): a simple ID (\"2009632251\", \"2005691065\") or a slash-separated path for newspaper issues (\"sn95047246/1935-09-05/ed-1\"). A loc.gov item link is also read as its id: \"https://www.loc.gov/item/2009632251/\", http or without \"www.\", or \"item/2009632251\"; so is an LCCN permalink, as its normalized LCCN: \"https://lccn.loc.gov/2005567251\", http or without a scheme; \"lccn.loc.gov/2005-568294\" reads as 2005568294. Any other URL, such as a /resource/ page URL, is rejected."Output schema / properties / date / descriptionPrevious value: -"Publication or creation date as LOC catalogs it: free text, a year, or a full date (e.g., \"1936 Apr.\", \"1909-1911.\", \"1894\", \"1912-04-16\")."New value: +"Publication or creation date as LOC catalogs it: free text, a year, or a full date (e.g., \"1936 Apr.\", \"1909-1911.\", \"1894\", \"1912-04-16\"). Absent when LOC records only a coded value (\"uuuu\", \"||||\") or none."Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `invalid_item_id`: item_id is neither a LOC item ID nor a loc.gov /item/ link: a URL on another loc.gov path (such as a /resource/ page URL) or another host, or text with characters or segments no LOC ID has. `item_not_found`: No item exists for the given ID. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. `upstream_unavailable`: The Library of Congress could not be reached, or answered with an error status, a bot challenge or other HTML page, or an unreadable response instead of its JSON. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_item_id`: item_id is not a LOC item ID, a loc.gov /item/ link, or an lccn.loc.gov permalink to an LCCN: a URL on another loc.gov or lccn.loc.gov path (such as a /resource/ page URL) or another host, an LCCN that does not normalize to up to three lowercase letters and 8 or 10 digits, or text with characters or segments no LOC ID has. `item_not_found`: No item exists for the given ID. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. `upstream_unavailable`: The Library of Congress could not be reached, or answered with an error status, a bot challenge or other HTML page, or an unreadable response instead of its JSON. Other values are possible when a failure originates below the handler."Output schema / properties / imprintAdded value: +{
+ "description": "Imprint as LOC catalogs it: place, publisher, and date of publication (e.g., \"New York : Werner School Book Company, c1900.\"), or a date alone on many photos and manuscripts (\"1936 Apr.\"). Absent when LOC records none.",
+ "type": "string"
+}Output schema / properties / item_id / descriptionPrevious value: -"LOC item ID: the input item_id, or the id read from the loc.gov item link passed as item_id."New value: +"LOC item ID: the input item_id, or the id read from the loc.gov item link or LCCN permalink passed as item_id."Output schema / properties / pages / items / properties / has_text / descriptionPrevious value: -"True when LOC holds OCR or transcribed text for this page."New value: +"True when LOC lists an OCR or transcribed text file for this page. A blank page can have one: LOC's blank-page placeholder, which libofcongress_get_newspaper_page returns as empty text."libofcongress_get_newspaper_page8 fields changedInput schema / properties / matchAdded value: +{
+ "description": "Return the passages around these terms instead of the whole page — pass the query you gave libofcongress_search_newspapers (e.g., titanic, or \"the titanic\" iceberg); the q= in a search result url is not read as match. Words separated by spaces are separate terms, any of which matches; a double-quoted span is one phrase. Each matches case-insensitively as literal text, with line breaks read as spaces; OCR misreads are not repaired. When set, ocr_text is empty, matches holds up to 10 passages of about 300 characters either side of each occurrence — when they need more, occurrences of the rarest terms come first, so a common word only fills the slots left — and match_count counts every occurrence. Omit match for the whole page. Up to 200 characters; blank is ignored.",
+ "maxLength": 200,
+ "type": "string"
+}Output schema / properties / item_idAdded value: +{
+ "description": "ID of the item this page belongs to: the newspaper issue (e.g., \"sn83030214/1912-04-16/ed-1\"), book, or manuscript volume (e.g., \"mm77093930\"). Pass it to libofcongress_get_item to list every page of the item, each with its page_url and has_text — for an article continued on a later page, or the next page of a book. Absent when LOC names no item.",
+ "type": "string"
+}Output schema / properties / item_titleAdded value: +{
+ "description": "Title of the item this page belongs to, on every page type: the book or manuscript title, or for a newspaper page the issue title with place and date (e.g., \"New-York tribune (New York [N.Y.]), April 16, 1912\"). Absent when LOC gives none.",
+ "type": "string"
+}Output schema / properties / match_countAdded value: +{
+ "description": "Present only when match is set: occurrences of every match term on the page, including those beyond the passages returned. 0 when nothing matched or the page has no text.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+}Output schema / properties / matchesAdded value: +{
+ "description": "Present only when match is set: passages of the page text around the occurrences of the match terms, in page order — about 300 characters either side of each occurrence, overlapping passages merged up to 1,200 characters, never overlapping, at most 10, chosen around the rarest terms first when more would be needed. Empty when nothing matched or the page has no text.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}Output schema / properties / notice / descriptionPrevious value: -"Set when ocr_available is true but ocr_text is empty, saying why: the text service did not answer this call (retry), its answer could not be read as text (retrying will not help), or the page's text is empty. Distinguishes these from a genuinely image-only page (where ocr_available is false). Absent when text was returned or the page has none."New value: +"Set when ocr_available is true but the page's text came back empty, saying why: the text service did not answer this call (retry), its answer could not be read as text (retrying will not help), or the page's text is empty — a blank page, including one LOC sends as the placeholder [NO TEXT AVAILABLE FOR THIS PAGE]. Distinguishes these from a genuinely image-only page (where ocr_available is false), which carries no notice. With match set on a page that has text, set instead when nothing matched or when some occurrences fall outside the passages returned — those are read on the whole page, by calling again without match. Absent otherwise."Output schema / properties / ocr_available / descriptionPrevious value: -"True when LOC holds OCR or transcribed text for this page. False for image-only pages where no text has been produced."New value: +"True when LOC lists OCR or transcribed text for this page, even if the text it returns is empty (see notice). False for image-only pages where no text has been produced."Output schema / properties / ocr_text / descriptionPrevious value: -"Full plain text of this page: OCR, or for some manuscripts a volunteer transcription. Empty string when ocr_available is false, or when the text could not be retrieved (see notice). May contain fragmented words, line-break artifacts, and misspellings inherent to historical OCR — do not attempt to repair."New value: +"Full plain text of this page: OCR, or for some manuscripts a volunteer transcription. Empty string when match is set (read matches instead), when ocr_available is false, or when the page is blank or its text could not be retrieved (see notice). May contain fragmented words, line-break artifacts, and misspellings inherent to historical OCR — do not attempt to repair."libofcongress_search_items3 fields changedOutput schema / properties / items / items / properties / date / descriptionPrevious value: -"Publication or creation date as LOC catalogs it: free text, a year, or a full date (e.g., \"c1915 Feb. 19.\", \"1912\")."New value: +"Publication or creation date as LOC catalogs it: free text, a year, or a full date (e.g., \"c1915 Feb. 19.\", \"1912\"). Absent when LOC records only a coded value (\"uuuu\", \"||||\") or none."Output schema / properties / items / items / properties / id / descriptionPrevious value: -"LOC identifier for this result. When is_item is true, pass it to libofcongress_get_item for full metadata. When is_item is false it is a non-item resource (a collection, exhibit, guide, or newspaper page), not a get_item input — open url instead."New value: +"LOC identifier for this result: an item ID, or the bare LCCN of a record whose url is an lccn.loc.gov permalink. When is_item is true, pass it to libofcongress_get_item for full metadata. When is_item is false it is a non-item resource (a collection, exhibit, guide, newspaper page, catalog.loc.gov record, or hdl.loc.gov finding aid), not a get_item input — open url instead."Output schema / properties / items / items / properties / is_item / descriptionPrevious value: -"True when this result is a catalog item whose id resolves through libofcongress_get_item. False for collections, exhibits, research guides, newspaper pages, and other non-item results, which have no get_item record — follow url instead. Always present on every result."New value: +"True when this result is a catalog item whose id resolves through libofcongress_get_item, including records LOC links by an lccn.loc.gov permalink. False for collections, exhibits, research guides, newspaper pages, catalog.loc.gov records, hdl.loc.gov finding aids, and other non-item results, which have no get_item record — follow url instead. Always present on every result."libofcongress_search_newspapers2 fields changedOutput schema / properties / items / items / properties / description / descriptionPrevious value: -"OCR text excerpt (~500 chars) for relevance assessment."New value: +"Opening of the page's OCR text (~500 chars): the page's first lines, not the text around the match. Pass the query as match to libofcongress_get_newspaper_page for the passages around it."Output schema / properties / items / items / properties / url / descriptionPrevious value: -"LOC resource URL for this page — pass to libofcongress_get_newspaper_page to get full OCR text."New value: +"LOC resource URL for this page — pass to libofcongress_get_newspaper_page for its full OCR text, or with the query as match for the passages around it."libofcongress_browse_collections6 fields changedInput schema / properties / limit / descriptionPrevious value: -"Maximum number of collections to return. Default 25, max 100."New value: +"Maximum number of collections to return. Default 25. A page holds at most 100 collections: a larger limit (up to 1000) is served as a 100-collection page, and page then counts 100-collection pages."Input schema / properties / limit / maximumPrevious value: -100New value: +1000Output schema / properties / effectiveLimitAdded value: +{
+ "description": "The page size actually served when limit exceeded the per-call cap of 100. Absent when limit was within the cap.",
+ "type": "number"
+}Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. `upstream_unavailable`: The Library of Congress could not be reached, or answered with an error status, a bot challenge or other HTML page, or an unreadable response instead of its JSON. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "rate_limit_exceeded",
- "server_busy",
- "request_timed_out"
-]New value: +[
+ "rate_limit_exceeded",
+ "server_busy",
+ "request_timed_out",
+ "upstream_unavailable"
+]Output schema / properties / notice / descriptionPrevious value: -"Recovery hint when results are empty or a page is out of range — suggests broadening the keyword or removing filters. Absent on successful result pages."New value: +"Recovery hint when results are empty or a page is out of range — suggests broadening the keyword or removing filters — plus disclosure of a capped limit. Absent on ordinary result pages."libofcongress_get_item19 fields changedInput schema / properties / include_filesAdded value: +{
+ "default": false,
+ "description": "Also list the download URLs of each listed page's files — every JPEG size, the JP2 and TIFF masters, OCR XML, and text files. Default false.",
+ "type": "boolean"
+}Input schema / properties / item_id / descriptionPrevious value: -"LOC item id from a libofcongress_search_items result's \"id\" field (where is_item is true). A simple ID (\"2009632251\", \"2005691065\") or a slash-separated path for newspaper pages (\"sn95047246/1935-09-05/ed-1\"). Pass the id verbatim; do not prepend the loc.gov URL or an \"item/\" prefix."New value: +"LOC item id from a libofcongress_search_items result's \"id\" field (where is_item is true): a simple ID (\"2009632251\", \"2005691065\") or a slash-separated path for newspaper issues (\"sn95047246/1935-09-05/ed-1\"). A loc.gov item link is also read as its id: \"https://www.loc.gov/item/2009632251/\", http or without \"www.\", or \"item/2009632251\". Any other URL, such as a /resource/ page URL, is rejected."Input schema / properties / page_limitAdded value: +{
+ "default": 50,
+ "description": "Pages to list. Default 50. A response lists at most 100 pages: a larger page_limit (up to 1000) is served as 100.",
+ "maximum": 1000,
+ "minimum": 1,
+ "type": "integer"
+}Input schema / properties / page_offsetAdded value: +{
+ "default": 0,
+ "description": "Index of the first page to list, 0-based across all of the item's resources. Default 0. Pass next_page_offset from the previous response to continue.",
+ "maximum": 9007199254740991,
+ "minimum": 0,
+ "type": "integer"
+}Output schema / anyOfPrevious value: -[
- {
- "not": {
- "required": [
- "error"
- ]
- },
- "required": [
- "item_id",
- "title",
- "contributors",
- "subject_headings",
- "notes",
- "languages",
- "locations",
- "former_ids",
- "original_formats",
- "online_formats",
- "resource_links",
- "related_items",
- "url"
- ]
- },
- {
- "required": [
- "error"
- ]
- }
-]New value: +[
+ {
+ "not": {
+ "required": [
+ "error"
+ ]
+ },
+ "required": [
+ "item_id",
+ "title",
+ "contributors",
+ "subject_headings",
+ "subject_terms",
+ "notes",
+ "languages",
+ "locations",
+ "former_ids",
+ "original_formats",
+ "online_formats",
+ "resources",
+ "pages",
+ "page_total",
+ "related_items",
+ "url",
+ "totalCount"
+ ]
+ },
+ {
+ "required": [
+ "error"
+ ]
+ }
+]Output schema / properties / date / descriptionPrevious value: -"Publication or creation date."New value: +"Publication or creation date as LOC catalogs it: free text, a year, or a full date (e.g., \"1936 Apr.\", \"1909-1911.\", \"1894\", \"1912-04-16\")."Output schema / properties / effectivePageLimitAdded value: +{
+ "description": "The page_limit actually served when page_limit exceeded the per-call cap of 100. Absent when page_limit was within the cap.",
+ "type": "number"
+}Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `item_not_found`: No item exists for the given ID. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_item_id`: item_id is neither a LOC item ID nor a loc.gov /item/ link: a URL on another loc.gov path (such as a /resource/ page URL) or another host, or text with characters or segments no LOC ID has. `item_not_found`: No item exists for the given ID. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. `upstream_unavailable`: The Library of Congress could not be reached, or answered with an error status, a bot challenge or other HTML page, or an unreadable response instead of its JSON. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "item_not_found",
- "rate_limit_exceeded",
- "server_busy",
- "request_timed_out"
-]New value: +[
+ "invalid_item_id",
+ "item_not_found",
+ "rate_limit_exceeded",
+ "server_busy",
+ "request_timed_out",
+ "upstream_unavailable"
+]Output schema / properties / item_id / descriptionPrevious value: -"LOC item ID as resolved by the service (matches the input item_id)."New value: +"LOC item ID: the input item_id, or the id read from the loc.gov item link passed as item_id."Output schema / properties / next_page_offsetAdded value: +{
+ "description": "page_offset for the next window of pages. Absent when this window reaches the last page.",
+ "type": "number"
+}Output schema / properties / noticeAdded value: +{
+ "description": "Set when page_offset is past the last page, or when page_limit was capped. Absent otherwise.",
+ "type": "string"
+}Output schema / properties / page_totalAdded value: +{
+ "description": "Pages across all of the item's resources.",
+ "type": "number"
+}Output schema / properties / pagesAdded value: +{
+ "description": "The window of the item's pages starting at page_offset, across every resource in order. Empty when the item has no pages or page_offset is past the last page.",
+ "items": {
+ "additionalProperties": false,
+ "description": "One page of the item.",
+ "properties": {
+ "files": {
+ "description": "Download URLs of the page's files: JPEG sizes, JP2 and TIFF masters, OCR XML, text. Present only when include_files is true.",
+ "items": {
+ "description": "Download URL; its extension names the format.",
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "has_text": {
+ "description": "True when LOC holds OCR or transcribed text for this page.",
+ "type": "boolean"
+ },
+ "page_url": {
+ "description": "LOC page URL. Pass to libofcongress_get_newspaper_page to read its text when has_text is true.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "page_url",
+ "has_text"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / resource_linksRemoved value: -{
- "description": "URLs to downloadable digital files (TIFF, JPEG, PDF). Empty when no digital surrogate exists.",
- "items": {
- "type": "string"
- },
- "type": "array"
-}Output schema / properties / resourcesAdded value: +{
+ "description": "The item's digital resources, in LOC order. Empty when no digital surrogate exists.",
+ "items": {
+ "additionalProperties": false,
+ "description": "One digital resource of the item, such as a photo, a volume, or a recording.",
+ "properties": {
+ "audio": {
+ "description": "Audio stream (MP3) of a sound recording. Absent when LOC gives none.",
+ "type": "string"
+ },
+ "image": {
+ "description": "Representative image URL. Absent when LOC gives none.",
+ "type": "string"
+ },
+ "page_count": {
+ "description": "Pages (file groups) in this resource.",
+ "type": "number"
+ },
+ "pdf": {
+ "description": "PDF of the whole resource. Absent when LOC gives none.",
+ "type": "string"
+ },
+ "url": {
+ "description": "LOC resource URL; its pages are this URL plus ?sp=N.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "url",
+ "page_count"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / subject_headings / descriptionPrevious value: -"LCSH subject headings assigned to this item."New value: +"Library of Congress Subject Headings (LCSH) assigned to this item, as cataloged (e.g., \"United States--History--Civil War, 1861-1865\"). Empty when the record carries none."Output schema / properties / subject_termsAdded value: +{
+ "description": "Subject terms LOC indexes this item under: lowercase heading components without dates (e.g., \"civil war\", \"united states\"). Each is a value the libofcongress_search_items subject filter accepts.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}Output schema / properties / totalCountAdded value: +{
+ "description": "Pages across all resources — mirrors output.page_total for agent reasoning.",
+ "type": "number"
+}libofcongress_get_newspaper_page9 fields changedInput schema / properties / page_url / descriptionPrevious value: -"The url field from a libofcongress_search_newspapers result (e.g., \"https://www.loc.gov/resource/sn83045462/1905-03-15/ed-1/seq-1/\"). Always pass the value directly from search results — do not construct or modify this URL."New value: +"A LOC page URL: the url field from a libofcongress_search_newspapers result (e.g., \"https://www.loc.gov/resource/sn83045462/1905-03-15/ed-1/?sp=1\"), or a pages[].page_url from libofcongress_get_item for a newspaper, book, or manuscript page (e.g., \"https://www.loc.gov/resource/mss93930.mss93930-001/?sp=3\"). Also accepted: the same /resource/ URL over http or without \"www.\", a newspaper page path ending /ed-N/seq-M/, and a Chronicling America page link (`chroniclingamerica.loc.gov/lccn/<lccn>/<date>/ed-N/seq-M/`); each is read as its https://www.loc.gov/resource/…/?sp=M page. Pass the value as returned — do not construct page URLs."Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `invalid_page_url`: page_url does not begin with https://www.loc.gov/resource/. `page_not_found`: The URL does not resolve to a valid LOC newspaper page resource. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_page_url`: page_url is not one LOC page: neither a loc.gov /resource/ URL nor a Chronicling America page link ending /ed-N/seq-M/. `page_not_found`: The URL does not resolve to a LOC page resource. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. `upstream_unavailable`: The Library of Congress could not be reached, or answered with an error status, a bot challenge or other HTML page, or an unreadable response instead of its JSON. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "invalid_page_url",
- "page_not_found",
- "rate_limit_exceeded",
- "server_busy",
- "request_timed_out"
-]New value: +[
+ "invalid_page_url",
+ "page_not_found",
+ "rate_limit_exceeded",
+ "server_busy",
+ "request_timed_out",
+ "upstream_unavailable"
+]Output schema / properties / notice / descriptionPrevious value: -"Set when ocr_available is true but ocr_text is empty — the page has digitized OCR, but the text service did not return it this call. Distinguishes a transient retrieval miss from a genuinely image-only page (where ocr_available is false). Absent when OCR text was returned or the page has no OCR."New value: +"Set when ocr_available is true but ocr_text is empty, saying why: the text service did not answer this call (retry), its answer could not be read as text (retrying will not help), or the page's text is empty. Distinguishes these from a genuinely image-only page (where ocr_available is false). Absent when text was returned or the page has none."Output schema / properties / ocr_available / descriptionPrevious value: -"True when digitized OCR text exists for this page. False for image-only digitization batches where OCR has not been applied."New value: +"True when LOC holds OCR or transcribed text for this page. False for image-only pages where no text has been produced."Output schema / properties / ocr_text / descriptionPrevious value: -"Full plain-text OCR content for the page. Empty string when ocr_available is false. May contain fragmented words, line-break artifacts, and misspellings inherent to historical OCR — do not attempt to repair."New value: +"Full plain text of this page: OCR, or for some manuscripts a volunteer transcription. Empty string when ocr_available is false, or when the text could not be retrieved (see notice). May contain fragmented words, line-break artifacts, and misspellings inherent to historical OCR — do not attempt to repair."Output schema / properties / page_url / descriptionPrevious value: -"The LOC resource URL for this newspaper page."New value: +"The LOC resource URL for this page, in the https://www.loc.gov/resource/…?sp=N form the input was read as."Output schema / properties / segment_count / descriptionPrevious value: -"Number of pages in the issue. Absent when LOC gives none."New value: +"Number of pages in the issue, volume, or folder. Absent when LOC gives none."Output schema / properties / sequence / descriptionPrevious value: -"Page sequence number within the issue."New value: +"Page sequence number within the issue, volume, or folder."libofcongress_search_items14 fields changedInput schema / properties / date_end / descriptionPrevious value: -"End year for date filter, inclusive (e.g., 1930). Omit for no upper bound."New value: +"End year for date filter, inclusive (e.g., 1930). Omit to run through the current year."Input schema / properties / include_facetsAdded value: +{
+ "default": false,
+ "description": "Also return subject_facets and location_facets: LOC's top subject and location terms across every match, with counts — the values the subject and location filters accept. Default false: facets add time to each search, so request them when you need filter values to narrow by.",
+ "type": "boolean"
+}Input schema / properties / limit / descriptionPrevious value: -"Results per page. Default 25, max 100."New value: +"Results per page. Default 25. A page holds at most 100 results: a larger limit (up to 1000) is served as a 100-result page, and page then counts 100-result pages."Input schema / properties / limit / maximumPrevious value: -100New value: +1000Input schema / properties / location / descriptionPrevious value: -"Geographic location filter (e.g., \"oklahoma\", \"washington d.c.\"). Lowercase, matches LOC location facets."New value: +"Geographic location filter (e.g., \"oklahoma\", \"washington d.c.\"). Lowercase, matches LOC location facets; location_facets (include_facets) lists values for a search."Input schema / properties / subject / descriptionPrevious value: -"Subject heading filter. Use the exact label from libofcongress_search_subjects results for best precision. Example: \"World War, 1939-1945\"."New value: +"Subject filter: an LCSH heading from libofcongress_search_subjects (e.g., \"World War, 1939-1945\", \"United States--History--Civil War, 1861-1865\") or a subject term from subject_facets (include_facets) or libofcongress_get_item subject_terms (e.g., \"world war\"). LOC indexes headings by their parts, so the value is split at \"--\" into lowercase terms with dates dropped, and an item must carry every term."Output schema / properties / effectiveLimitAdded value: +{
+ "description": "The page size actually served when limit exceeded the per-call cap of 100. Absent when limit was within the cap.",
+ "type": "number"
+}Output schema / properties / effectiveSubjectTermsAdded value: +{
+ "description": "The subject terms the subject filter was sent as, all required to match. Absent when no subject filter was given.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `invalid_date_range`: date_start is later than date_end. `incompatible_filters`: format and collection_slug were both supplied; each selects a different LOC endpoint, so only one can apply. `collection_not_found`: collection_slug does not resolve to a LOC collection. Reported on page 1; a later page gets the out-of-range notice, since LOC answers both cases the same way there. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_date_range`: date_start is later than date_end, or date_start is given alone and is later than the current year. `incompatible_filters`: format and collection_slug were both supplied; each selects a different LOC endpoint, so only one can apply. `collection_not_found`: collection_slug does not resolve to a LOC collection. Reported on page 1; a later page gets the out-of-range notice, since LOC answers both cases the same way there. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. `upstream_unavailable`: The Library of Congress could not be reached, or answered with an error status, a bot challenge or other HTML page, or an unreadable response instead of its JSON. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "invalid_date_range",
- "incompatible_filters",
- "collection_not_found",
- "rate_limit_exceeded",
- "server_busy",
- "request_timed_out"
-]New value: +[
+ "invalid_date_range",
+ "incompatible_filters",
+ "collection_not_found",
+ "rate_limit_exceeded",
+ "server_busy",
+ "request_timed_out",
+ "upstream_unavailable"
+]Output schema / properties / items / items / properties / date / descriptionPrevious value: -"Publication or creation date."New value: +"Publication or creation date as LOC catalogs it: free text, a year, or a full date (e.g., \"c1915 Feb. 19.\", \"1912\")."Output schema / properties / location_facetsAdded value: +{
+ "description": "LOC's top location terms across every item matching this search (up to 10), most frequent first. Pass a value as the location filter to narrow the search. Present only when include_facets is true; empty when LOC reports none.",
+ "items": {
+ "additionalProperties": false,
+ "description": "One location facet value.",
+ "properties": {
+ "count": {
+ "description": "Matching items carrying this location term.",
+ "type": "number"
+ },
+ "value": {
+ "description": "The location term, as the location filter accepts it.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "value",
+ "count"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / notice / descriptionPrevious value: -"Recovery hint when results are empty or a page is out of range — echoes applied filters and suggests how to broaden. Absent on successful result pages."New value: +"Recovery hint when results are empty or a page is out of range — echoes applied filters, subject terms and location included, and suggests how to broaden — plus disclosure of a capped limit or of the retrieval ceiling. Absent on ordinary result pages."Output schema / properties / subject_facetsAdded value: +{
+ "description": "LOC's top subject terms across every item matching this search (up to 10), most frequent first. Pass a value as the subject filter to narrow the search. Present only when include_facets is true; empty when LOC reports none.",
+ "items": {
+ "additionalProperties": false,
+ "description": "One subject facet value.",
+ "properties": {
+ "count": {
+ "description": "Matching items carrying this subject term.",
+ "type": "number"
+ },
+ "value": {
+ "description": "The subject term, as the subject filter accepts it.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "value",
+ "count"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}libofcongress_search_newspapers19 fields changedInput schema / properties / date_end / anyOfAdded value: +[
+ {
+ "description": "A year, e.g., 1912.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ {
+ "description": "A date: \"YYYY\", \"YYYY-MM\", or \"YYYY-MM-DD\", e.g., \"1912-04-16\".",
+ "pattern": "^(\\d{4})(?:-(\\d{1,2})(?:-(\\d{1,2}))?)?$",
+ "type": "string"
+ },
+ {
+ "const": "",
+ "type": "string"
+ }
+]Input schema / properties / date_end / descriptionPrevious value: -"End year for date filter, inclusive (e.g., 1920). Omit for no upper bound."New value: +"End of the date filter, inclusive, in the same forms as date_start (e.g., 1920 or \"1912-04-16\"). A year or month ends on its last day, so \"1912-04\" runs through April 30. Omit to run through the current year."Input schema / properties / date_end / maximumRemoved value: -9007199254740991Input schema / properties / date_end / minimumRemoved value: --9007199254740991Input schema / properties / date_end / typeRemoved value: -"integer"Input schema / properties / date_start / anyOfAdded value: +[
+ {
+ "description": "A year, e.g., 1912.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ {
+ "description": "A date: \"YYYY\", \"YYYY-MM\", or \"YYYY-MM-DD\", e.g., \"1912-04-16\".",
+ "pattern": "^(\\d{4})(?:-(\\d{1,2})(?:-(\\d{1,2}))?)?$",
+ "type": "string"
+ },
+ {
+ "const": "",
+ "type": "string"
+ }
+]Input schema / properties / date_start / descriptionPrevious value: -"Start year for date filter, inclusive (e.g., 1900). Omit for no lower bound."New value: +"Start of the date filter, inclusive: an integer year (e.g., 1900) or a \"YYYY\", \"YYYY-MM\", or \"YYYY-MM-DD\" string (e.g., \"1912-04-15\"); month and day may be one or two digits. A year or month starts on its first day. Omit for no lower bound."Input schema / properties / date_start / maximumRemoved value: -9007199254740991Input schema / properties / date_start / minimumRemoved value: --9007199254740991Input schema / properties / date_start / typeRemoved value: -"integer"Input schema / properties / limit / descriptionPrevious value: -"Results per page. Default 25, max 100."New value: +"Results per page. Default 25. A page holds at most 100 results: a larger limit (up to 1000) is served as a 100-result page, and page then counts 100-result pages."Input schema / properties / limit / maximumPrevious value: -100New value: +1000Input schema / properties / newspaper_title / descriptionPrevious value: -"Filter to a specific newspaper by title (partial match accepted)."New value: +"Filter to one newspaper. Pass the newspaper_title value of a libofcongress_search_newspapers result exactly (case-insensitive), e.g., \"new-york tribune (new york [n.y.]) 1866-1924\" — the full catalog title with place and run. A shortened title such as \"New-York Tribune\" matches nothing."Input schema / properties / state / descriptionPrevious value: -"Filter to newspapers published in this US state. Use the full state name, lowercase (e.g., \"oklahoma\", \"new york\")."New value: +"Filter to newspapers LOC indexes under this US state: the full state name (e.g., \"oklahoma\", \"new york\") or its two-letter postal code (e.g., \"OK\", \"NY\"), case-insensitive. Use \"district of columbia\" (or \"DC\") for Washington, D.C.; \"washington\" means Washington state. City and county names match nothing."Output schema / properties / effectiveLimitAdded value: +{
+ "description": "The page size actually served when limit exceeded the per-call cap of 100. Absent when limit was within the cap.",
+ "type": "number"
+}Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `invalid_date_range`: date_start is later than date_end. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_date`: date_start or date_end names no calendar day: a month outside 01-12, or a day past the end of its month (e.g., \"1912-02-30\"). `invalid_date_range`: date_start is later than date_end, or date_start is given alone and is later than the current year. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. `upstream_unavailable`: The Library of Congress could not be reached, or answered with an error status, a bot challenge or other HTML page, or an unreadable response instead of its JSON. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "invalid_date_range",
- "rate_limit_exceeded",
- "server_busy",
- "request_timed_out"
-]New value: +[
+ "invalid_date",
+ "invalid_date_range",
+ "rate_limit_exceeded",
+ "server_busy",
+ "request_timed_out",
+ "upstream_unavailable"
+]Output schema / properties / items / items / properties / newspaper_title / descriptionPrevious value: -"Newspaper publication title."New value: +"The newspaper's full catalog title with place and run (e.g., \"the seattle star (seattle, wash.) 1899-1947\"). Pass it unchanged as newspaper_title to search only this paper."Output schema / properties / notice / descriptionPrevious value: -"Recovery hint when results are empty or a page is out of range — echoes applied filters and suggests how to broaden. Absent on successful result pages."New value: +"Recovery hint when results are empty or a page is out of range — echoes applied filters and suggests how to broaden — plus disclosure of a capped limit or of the retrieval ceiling. Absent on ordinary result pages."libofcongress_search_subjects10 fields changedInput schema / properties / limit / descriptionPrevious value: -"Maximum number of subject headings to return. Default 10, max 50."New value: +"Maximum number of subject headings to return. Default 10. A call returns at most 50 headings; a larger limit (up to 1000) returns up to 50."Input schema / properties / limit / maximumPrevious value: -50New value: +1000Output schema / properties / cap / descriptionPrevious value: -"The limit applied to this response — maximum headings the API will return."New value: +"The heading limit applied to this response."Output schema / properties / effectiveLimitAdded value: +{
+ "description": "The heading count actually applied when limit exceeded the per-call cap of 50. Absent when limit was within the cap.",
+ "type": "number"
+}Output schema / properties / effectiveQuery / descriptionPrevious value: -"The keyword query as submitted to the id.loc.gov suggest endpoint, after trimming."New value: +"The query as submitted to the id.loc.gov subject suggest endpoint, after trimming."Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `request_timed_out`: The Library of Congress subject heading service did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `request_timed_out`: The Library of Congress subject heading service did not respond within the 50-second request budget. `upstream_unavailable`: The Library of Congress subject heading service could not be reached, or answered with an error status, an HTML page, or an unreadable response instead of its JSON. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "request_timed_out"
-]New value: +[
+ "request_timed_out",
+ "upstream_unavailable"
+]Output schema / properties / notice / descriptionPrevious value: -"Recovery hint when results are empty, or when the upstream candidate cap under-filled the request. Distinguishes \"exhausted by ranking\" (retry with a more specific query) from \"no LCSH coverage\", and suggests inverted-form strategies. Absent when the full requested set was returned."New value: +"Recovery hint when no heading matched; how many headings matched when more exist than this response holds; disclosure of a capped limit. Absent when every matching heading was returned."Output schema / properties / subjects / descriptionPrevious value: -"LCSH subject headings matching the query, ordered by relevance. To see how many LOC items carry a heading, pass its label as the libofcongress_search_items subject filter and read total."New value: +"LCSH subject headings matching the query, ordered by relevance, an exact match first. To see how many LOC items carry a heading, pass its label as the libofcongress_search_items subject filter and read total."Output schema / properties / truncated / descriptionPrevious value: -"True when results were capped at the requested limit. Increase limit or refine the query to surface additional headings."New value: +"True when more headings match than this response holds. Refine the query to see others, or raise limit when it is below 50."libofcongress_browse_collections2 fields changedOutput schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "rate_limit_exceeded"
-]New value: +[
+ "rate_limit_exceeded",
+ "server_busy",
+ "request_timed_out"
+]libofcongress_get_item3 fields changedInput schema / properties / item_id / descriptionPrevious value: -"LOC item id from a libofcongress_search result's \"id\" field (where is_item is true). A simple ID (\"2009632251\", \"2005691065\") or a slash-separated path for newspaper pages (\"sn95047246/1935-09-05/ed-1\"). Pass the id verbatim; do not prepend the loc.gov URL or an \"item/\" prefix."New value: +"LOC item id from a libofcongress_search_items result's \"id\" field (where is_item is true). A simple ID (\"2009632251\", \"2005691065\") or a slash-separated path for newspaper pages (\"sn95047246/1935-09-05/ed-1\"). Pass the id verbatim; do not prepend the loc.gov URL or an \"item/\" prefix."Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `item_not_found`: No item exists for the given ID. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `item_not_found`: No item exists for the given ID. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "item_not_found",
- "rate_limit_exceeded"
-]New value: +[
+ "item_not_found",
+ "rate_limit_exceeded",
+ "server_busy",
+ "request_timed_out"
+]libofcongress_get_newspaper_page2 fields changedOutput schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `invalid_page_url`: page_url does not begin with https://www.loc.gov/resource/. `page_not_found`: The URL does not resolve to a valid LOC newspaper page resource. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_page_url`: page_url does not begin with https://www.loc.gov/resource/. `page_not_found`: The URL does not resolve to a valid LOC newspaper page resource. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "invalid_page_url",
- "page_not_found",
- "rate_limit_exceeded"
-]New value: +[
+ "invalid_page_url",
+ "page_not_found",
+ "rate_limit_exceeded",
+ "server_busy",
+ "request_timed_out"
+]libofcongress_searchlibofcongress_search_itemslibofcongress_search_newspapers2 fields changedOutput schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `invalid_date_range`: date_start is later than date_end. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_date_range`: date_start is later than date_end. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "invalid_date_range",
- "rate_limit_exceeded"
-]New value: +[
+ "invalid_date_range",
+ "rate_limit_exceeded",
+ "server_busy",
+ "request_timed_out"
+]libofcongress_search_subjects4 fields changedOutput schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode."New value: +"Machine-readable failure mode. Declared by this tool: `request_timed_out`: The Library of Congress subject heading service did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesAdded value: +[
+ "request_timed_out"
+]Output schema / properties / subjects / descriptionPrevious value: -"LCSH subject headings matching the query, ordered by relevance. To see how many LOC items carry a heading, pass its label as the libofcongress_search subject filter and read total."New value: +"LCSH subject headings matching the query, ordered by relevance. To see how many LOC items carry a heading, pass its label as the libofcongress_search_items subject filter and read total."Output schema / properties / subjects / items / properties / label / descriptionPrevious value: -"Standardized LCSH heading — use this exact string in the libofcongress_search subject filter."New value: +"Standardized LCSH heading — use this exact string in the libofcongress_search_items subject filter."libofcongress_get_item3 fields changedInput schema / properties / item_id / descriptionPrevious value: -"LOC item id from a libofcongress_search result's \"id\" field (where is_item is true). A simple ID (\"2009632251\", \"loc.pnp.ppmsc.02404\") or a slash-separated path for newspaper pages (\"sn95047246/1935-09-05/ed-1\"). Pass the id verbatim; do not prepend the loc.gov URL or an \"item/\" prefix."New value: +"LOC item id from a libofcongress_search result's \"id\" field (where is_item is true). A simple ID (\"2009632251\", \"2005691065\") or a slash-separated path for newspaper pages (\"sn95047246/1935-09-05/ed-1\"). Pass the id verbatim; do not prepend the loc.gov URL or an \"item/\" prefix."Output schema / properties / contributors / descriptionPrevious value: -"Names of contributors, creators, or photographers."New value: +"Contributors, creators, or photographers as LOC catalogs them, role included (e.g., \"Washington, George, 1732-1799 (Author)\"). One person can appear once per role. Empty when LOC lists none."Output schema / properties / related_items / descriptionPrevious value: -"IDs or URLs of related LOC items for follow-up retrieval."New value: +"IDs or URLs of related LOC records for follow-up retrieval; a title stands in for a related record LOC gives neither for."libofcongress_get_newspaper_page9 fields changedOutput schema / properties / date / descriptionPrevious value: -"Issue publication date."New value: +"Issue publication date (YYYY-MM-DD)."Output schema / properties / edition / descriptionPrevious value: -"Edition or publication context identifier."New value: +"Edition number of the issue (e.g., \"1\"). Absent when LOC gives none."Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `page_not_found`: The URL does not resolve to a valid LOC newspaper page resource. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_page_url`: page_url does not begin with https://www.loc.gov/resource/. `page_not_found`: The URL does not resolve to a valid LOC newspaper page resource. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "page_not_found",
- "rate_limit_exceeded"
-]New value: +[
+ "invalid_page_url",
+ "page_not_found",
+ "rate_limit_exceeded"
+]Output schema / properties / newspaper_title / descriptionPrevious value: -"Title of the newspaper publication."New value: +"Title of the newspaper publication. Absent when LOC gives none."Output schema / properties / place_of_publicationAdded value: +{
+ "description": "Where the newspaper was published, as LOC catalogs it (e.g., \"Charleston, S.C.\"). Absent when LOC gives none.",
+ "type": "string"
+}Output schema / properties / segment_countAdded value: +{
+ "description": "Number of pages in the issue. Absent when LOC gives none.",
+ "type": "number"
+}Output schema / properties / stateRemoved value: -{
- "description": "State where the newspaper was published.",
- "type": "string"
-}Output schema / properties / statesAdded value: +{
+ "description": "Every US state LOC indexes this newspaper title under (e.g., [\"georgia\", \"south carolina\"]), in LOC order — possibly more than the state of publication. Absent when LOC lists no state.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}libofcongress_search2 fields changedOutput schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `incompatible_filters`: format and collection_slug were both supplied; each selects a different LOC endpoint, so only one can apply. `collection_not_found`: collection_slug does not resolve to a LOC collection. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_date_range`: date_start is later than date_end. `incompatible_filters`: format and collection_slug were both supplied; each selects a different LOC endpoint, so only one can apply. `collection_not_found`: collection_slug does not resolve to a LOC collection. Reported on page 1; a later page gets the out-of-range notice, since LOC answers both cases the same way there. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "incompatible_filters",
- "collection_not_found",
- "rate_limit_exceeded"
-]New value: +[
+ "invalid_date_range",
+ "incompatible_filters",
+ "collection_not_found",
+ "rate_limit_exceeded"
+]libofcongress_search_newspapers4 fields changedOutput schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_date_range`: date_start is later than date_end. `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "rate_limit_exceeded"
-]New value: +[
+ "invalid_date_range",
+ "rate_limit_exceeded"
+]Output schema / properties / items / items / properties / stateRemoved value: -{
- "description": "State where the newspaper was published.",
- "type": "string"
-}Output schema / properties / items / items / properties / statesAdded value: +{
+ "description": "Every US state LOC indexes this newspaper title under (e.g., [\"georgia\", \"south carolina\"]), in LOC order. A title indexed against its circulation area lists several, so no entry is necessarily the place of publication — libofcongress_get_newspaper_page returns place_of_publication. Absent when LOC lists no state.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}libofcongress_search_subjects2 fields changedOutput schema / properties / subjects / descriptionPrevious value: -"LCSH subject headings matching the query, ordered by relevance."New value: +"LCSH subject headings matching the query, ordered by relevance. To see how many LOC items carry a heading, pass its label as the libofcongress_search subject filter and read total."Output schema / properties / subjects / items / properties / countRemoved value: -{
- "description": "Approximate number of LOC items carrying this heading. Omitted when unavailable.",
- "type": "number"
-}libofcongress_browse_collectionslibofcongress_get_itemlibofcongress_get_newspaper_pagelibofcongress_searchlibofcongress_search_newspaperslibofcongress_search_subjectsChronicling America MCP — full-text search of ~150 years of digitized U.S. newspapers…
Search 14.5M Smithsonian Open Access objects, get CC0 images, find cross-collection connections.
US National Archives Catalog (NARA): search the federal government's permanent records…
Search books and authors across Open Library, the Internet Archive open catalog.
Add one secure layer between your agents and this server.