Skip to main content
Glama

Secedgar Get Filing

secedgar_get_filing
Read-onlyIdempotent

Fetch a specific filing's metadata and document content by accession number. Returns the primary document as readable text. Use offset/next_offset for multi-page access to large filings (10-K, S-1 can exceed 1M chars): pass the next_offset from a truncated response as offset, without section or find, to read the next page. Use section to jump directly to a heading (e.g. 'risk factors', 'item 7') without needing an offset, or find to open the page at a phrase in the text (e.g. 'net revenue retention') and list where it occurs.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "accession_number": "<accession_number>"
    },
    "name": "secedgar_get_filing"
  }
}

Input Schema

NameRequiredDescriptionDefault
cikNoFiler CIK, digits only (resolve via secedgar_company_search if you have a ticker or name). Optional but recommended — speeds up archive lookup. If omitted, the filer is looked up from the accession number through EDGAR full-text search (2001 onward) and the accession number's own prefix, which for many filings is a filing agent's CIK, and when none of those directories serves the filing, through the filers its index page names.
findNoOpen the page at a phrase in the document's text (e.g. 'net revenue retention') and list where it occurs. Matched as a substring, ignoring case, whitespace runs, and quote style, so a phrase broken across a line matches; no patterns or whole-word matching. The page opens at the first occurrence at or after offset — at its line's start when that is at most 200 characters earlier, else at the first word starting within those 200 — and occurrences lists up to 20 from there with context, occurrences_total counting the whole document. Blank reads as omitted. With find, offset is where the search starts, so leave find out when paging on with next_offset; section takes precedence over find.
offsetNoCharacter offset into the extracted document text. Pass next_offset from a truncated response to continue reading the next page, and leave section and find out: section takes precedence over offset, and with find, offset is where the search starts. Default 0 reads from the beginning.
sectionNoJump to a named section, matched against every detected heading and the document's own lines (e.g. 'risk factors', 'item 7', 'item 2.02', 'certain relationships'). The first match wins, in this order: a heading equal to the value, or whose title after its Item/Part marker equals it; the first Item or Part heading containing it; a document line equal to it — a subheading the outline omits ('Liquidity and Capital Resources') — unless the line labels a table row; the first other heading containing it; a table-row label equal to it, else a document line starting with it. In a proxy statement (DEF 14A and its variants), whose ITEM headings are ballot proposals, the first heading of any kind containing the value comes before both document-line steps. Within each heading step a body heading wins over a table-of-contents row, which lands only when nothing else at that step matches; a table-of-contents row that links to its section lands on that section. A line landing says so in the notice; table-of-contents rows and wrapped cross-references are never line landings. A leading 20-F sub-item label on a heading or line ('3D.', 'B.') is ignored, so 'risk factors' reaches '3D. RISK FACTORS'; the value itself is matched as given. A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16, and 'part i' never reaches Part II. Every step ignores case, whitespace, and quote style, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones; the steps comparing a whole heading or line (equal to, starting with) also ignore the punctuation between an Item or Part marker and its title, so 'Item 1A Risk Factors' reaches 'Item 1A. – Risk Factors'. For a phrase in the text that is not a heading, use find. Takes precedence over find and offset, so leave it out when paging on with next_offset. On a miss, the error message includes the detected outline so you can pick the correct heading.
documentNoSpecific document filename within the filing (e.g., "ex-21.htm" for subsidiaries list). Omitted or blank: the primary document. Available documents are listed in the response metadata under documents, and a primary_document value is accepted too; entries marked binary hold no text and are rejected.
include_xbrlNoInclude XBRL viewer artifacts and machine-readable taxonomy files (R*.htm fragments, *_cal/_def/_lab/_pre.xml linkbases, *_htm.xml inline instance, *.xsd schemas, MetaLinks.json, FilingSummary.xml, Show.js, report.css, *-xbrl.zip, Financial_Report.xlsx, EX-101.* technical exhibits) under documents.xbrl. Off by default — these dominate filing indexes (~100 entries on a typical 10-K) and are rarely relevant when reading filing content.
content_limitNoMaximum characters of document text to return per page. 10-K filings can exceed 500,000 characters; S-1/A can exceed 1,000,000. Default 50,000 captures ~12,000 words (typically business overview, risk factors, and MD&A). Increase to 200,000 for full financial statements, or decrease for quick summaries. Page on with offset; section and find open a page at a heading or a phrase. Capped at 200000: a larger value, up to 1000000, returns what 200000 returns.
accession_numberYesFiling accession number in either format: "0000320193-23-000106" (dashes) or "000032019323000106" (no dashes). Obtained from secedgar_company_search or secedgar_search_filings results.

Output Schema

NameRequiredDescriptionDefault
capNoThe `content_limit` that was applied.
cikNoFiling entity CIK, zero-padded to 10 digits.
formNoForm type (e.g., "10-K"), from the submissions feed or the filing's SEC header. Absent only when neither has it.
errorNoPresent when the call failed. Absent on success.
shownNoCharacters of document text returned on this page.
noticeNoHow to read the next page or list more occurrences of find, which file was read when the archive does not serve the indexed primary, when section landed on a document line rather than a detected heading, and how many headings were detected when the outline lists fewer.
contentNoDocument text content for this page window.
outlineNoUp to 50 detected headings on a truncated first page (offset=0, no section or find). Past 50: Item and Part headings first (bare TOC copies of titled ones dropped), then the earliest; the notice gives the count. Pass text as section (a linked TOC row lands on its section) or offset as offset.
documentsNoFiling documents by category. Any name is a valid document input except entries with binary: true, which fail with binary_document; scans can outnumber readable documents.
truncatedNoTrue when the document is longer than `content_limit` allowed through.
filing_urlNoDirect URL to the filing on SEC.gov.
filing_dateNoDate the filing was submitted (YYYY-MM-DD). Absent under the same conditions as form.
next_offsetNoOffset of the next page, to pass as offset without section or find; present while content_truncated is true.
occurrencesNoWith find: up to 20 occurrences, from the one the page opens at.
company_nameNoFiling entity name. Absent if the CIK did not resolve to a known entity.
period_endingNoPeriod of report (YYYY-MM-DD), from the same source as form. Absent for forms without one (S-8, Form 4, proxy statements) or when neither source has it.
accession_numberNoFiling accession number, normalized to dash format.
primary_documentNoPrimary document as read: an XML form's SEC rendering (xsl…/form4.xml) up to 600 KB raw; a 2000–2001 name SEC does not serve, as <accession>-<name>, else the full submission <accession>.txt.
content_truncatedNoTrue if content was truncated at content_limit.
occurrences_totalNoWith find: occurrences in the whole document.
requested_documentNoFilename requested via document. Present only when it differs from primary_document.
content_total_lengthNoFull document length in characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed27 schema fields changed
    • changedInput schema / properties / content_limit / description
      Previous value: -"Maximum characters of document text to return per page. 10-K filings can exceed 500,000 characters; S-1/A can exceed 1,000,000. Default 50,000 captures ~12,000 words (typically business overview, risk factors, and MD&A). Increase to 200,000 for full financial statements, or decrease for quick summaries. Use offset or section for subsequent pages. Capped at 200000: a larger value, up to 1000000, returns what 200000 returns."New value: +"Maximum characters of document text to return per page. 10-K filings can exceed 500,000 characters; S-1/A can exceed 1,000,000. Default 50,000 captures ~12,000 words (typically business overview, risk factors, and MD&A). Increase to 200,000 for full financial statements, or decrease for quick summaries. Page on with offset; section and find open a page at a heading or a phrase. Capped at 200000: a larger value, up to 1000000, returns what 200000 returns."
    • addedInput schema / properties / find
      Added value: +{
      +  "description": "Open the page at a phrase in the document's text (e.g. 'net revenue retention') and list where it occurs. Matched as a substring, ignoring case, whitespace runs, and quote style, so a phrase broken across a line matches; no patterns or whole-word matching. The page opens at the first occurrence at or after offset — at its line's start when that is at most 200 characters earlier, else at the first word starting within those 200 — and occurrences lists up to 20 from there with context, occurrences_total counting the whole document. Blank reads as omitted. With find, offset is where the search starts, so leave find out when paging on with next_offset; section takes precedence over find.",
      +  "maxLength": 200,
      +  "type": "string"
      +}
    • changedInput schema / properties / offset / description
      Previous value: -"Character offset into the extracted document text. Pass next_offset from a truncated response to continue reading the next page, and leave section out: section takes precedence over offset. Default 0 reads from the beginning."New value: +"Character offset into the extracted document text. Pass next_offset from a truncated response to continue reading the next page, and leave section and find out: section takes precedence over offset, and with find, offset is where the search starts. Default 0 reads from the beginning."
    • changedInput schema / properties / section / description
      Previous value: -"Jump to a named section, matched against every detected heading and the document's own lines (e.g. 'risk factors', 'item 7', 'item 2.02', 'certain relationships'). The first match wins, in this order: a heading equal to the value, or whose title after its Item/Part marker equals it; the first Item or Part heading containing it; a document line equal to it — a subheading the outline omits ('Liquidity and Capital Resources') — unless the line labels a table row; the first other heading containing it; a table-row label equal to it, else a document line starting with it. In a proxy statement (DEF 14A and its variants), whose ITEM headings are ballot proposals, the first heading of any kind containing the value comes before both document-line steps. Within each heading step a body heading wins over a table-of-contents row, which lands only when nothing else at that step matches. A line landing says so in the notice; table-of-contents rows and wrapped cross-references are never line landings. A leading 20-F sub-item label on a heading or line ('3D.', 'B.') is ignored, so 'risk factors' reaches '3D. RISK FACTORS'; the value itself is matched as given. A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16, and 'part i' never reaches Part II. Every step ignores case, whitespace, and quote style, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones; the steps comparing a whole heading or line (equal to, starting with) also ignore the punctuation between an Item or Part marker and its title, so 'Item 1A Risk Factors' reaches 'Item 1A. – Risk Factors'. Takes precedence over offset when both are provided, so leave it out when paging on with next_offset. On a miss, the error message includes the detected outline so you can pick the correct heading."New value: +"Jump to a named section, matched against every detected heading and the document's own lines (e.g. 'risk factors', 'item 7', 'item 2.02', 'certain relationships'). The first match wins, in this order: a heading equal to the value, or whose title after its Item/Part marker equals it; the first Item or Part heading containing it; a document line equal to it — a subheading the outline omits ('Liquidity and Capital Resources') — unless the line labels a table row; the first other heading containing it; a table-row label equal to it, else a document line starting with it. In a proxy statement (DEF 14A and its variants), whose ITEM headings are ballot proposals, the first heading of any kind containing the value comes before both document-line steps. Within each heading step a body heading wins over a table-of-contents row, which lands only when nothing else at that step matches; a table-of-contents row that links to its section lands on that section. A line landing says so in the notice; table-of-contents rows and wrapped cross-references are never line landings. A leading 20-F sub-item label on a heading or line ('3D.', 'B.') is ignored, so 'risk factors' reaches '3D. RISK FACTORS'; the value itself is matched as given. A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16, and 'part i' never reaches Part II. Every step ignores case, whitespace, and quote style, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones; the steps comparing a whole heading or line (equal to, starting with) also ignore the punctuation between an Item or Part marker and its title, so 'Item 1A Risk Factors' reaches 'Item 1A. – Risk Factors'. For a phrase in the text that is not a heading, use find. Takes precedence over find and offset, so leave it out when paging on with next_offset. On a miss, the error message includes the detected outline so you can pick the correct heading."
    • changedOutput schema / properties / documents / properties / auxiliary / items / description
      Previous value: -"One document entry from the filing."New value: +"One filing document."
    • changedOutput schema / properties / documents / properties / auxiliary / items / properties / description / description
      Previous value: -"SEC description (e.g., \"Subsidiaries of the Registrant\"). Absent when none."New value: +"SEC description, e.g. \"Subsidiaries of the Registrant\"."
    • changedOutput schema / properties / documents / properties / auxiliary / items / properties / name / description
      Previous value: -"Document filename within the filing archive."New value: +"Filename in the filing archive."
    • changedOutput schema / properties / documents / properties / auxiliary / items / properties / type / description
      Previous value: -"SEC document type (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\"), or without a submission header a filename-inferred label (\"exhibit\", \"PDF\", \"unknown\")."New value: +"SEC type (\"10-K\", \"EX-21.1\", \"GRAPHIC\"); with no submission header, a filename label (\"exhibit\", \"PDF\", \"unknown\")."
    • changedOutput schema / properties / documents / properties / exhibits / items / description
      Previous value: -"One document entry from the filing."New value: +"One filing document."
    • changedOutput schema / properties / documents / properties / exhibits / items / properties / description / description
      Previous value: -"SEC description (e.g., \"Subsidiaries of the Registrant\"). Absent when none."New value: +"SEC description, e.g. \"Subsidiaries of the Registrant\"."
    • changedOutput schema / properties / documents / properties / exhibits / items / properties / name / description
      Previous value: -"Document filename within the filing archive."New value: +"Filename in the filing archive."
    • changedOutput schema / properties / documents / properties / exhibits / items / properties / type / description
      Previous value: -"SEC document type (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\"), or without a submission header a filename-inferred label (\"exhibit\", \"PDF\", \"unknown\")."New value: +"SEC type (\"10-K\", \"EX-21.1\", \"GRAPHIC\"); with no submission header, a filename label (\"exhibit\", \"PDF\", \"unknown\")."
    • changedOutput schema / properties / documents / properties / primary / items / description
      Previous value: -"One document entry from the filing."New value: +"One filing document."
    • changedOutput schema / properties / documents / properties / primary / items / properties / description / description
      Previous value: -"SEC description (e.g., \"Subsidiaries of the Registrant\"). Absent when none."New value: +"SEC description, e.g. \"Subsidiaries of the Registrant\"."
    • changedOutput schema / properties / documents / properties / primary / items / properties / name / description
      Previous value: -"Document filename within the filing archive."New value: +"Filename in the filing archive."
    • changedOutput schema / properties / documents / properties / primary / items / properties / type / description
      Previous value: -"SEC document type (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\"), or without a submission header a filename-inferred label (\"exhibit\", \"PDF\", \"unknown\")."New value: +"SEC type (\"10-K\", \"EX-21.1\", \"GRAPHIC\"); with no submission header, a filename label (\"exhibit\", \"PDF\", \"unknown\")."
    • changedOutput schema / properties / documents / properties / xbrl / items / description
      Previous value: -"One document entry from the filing."New value: +"One filing document."
    • changedOutput schema / properties / documents / properties / xbrl / items / properties / description / description
      Previous value: -"SEC description (e.g., \"Subsidiaries of the Registrant\"). Absent when none."New value: +"SEC description, e.g. \"Subsidiaries of the Registrant\"."
    • changedOutput schema / properties / documents / properties / xbrl / items / properties / name / description
      Previous value: -"Document filename within the filing archive."New value: +"Filename in the filing archive."
    • changedOutput schema / properties / documents / properties / xbrl / items / properties / type / description
      Previous value: -"SEC document type (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\"), or without a submission header a filename-inferred label (\"exhibit\", \"PDF\", \"unknown\")."New value: +"SEC type (\"10-K\", \"EX-21.1\", \"GRAPHIC\"); with no submission header, a filename label (\"exhibit\", \"PDF\", \"unknown\")."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive. `no_documents`: Filing index lists items but no fetchable primary document was found. `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return. `filing_not_found`: No filing matches the accession number under any candidate CIK. `offset_out_of_range`: The provided offset is at or beyond the end of the document. `section_not_found`: The section string matched no detected heading and no line of the document. `rate_limited`: SEC is rate-limiting this server's IP — SEC answered 429, or the call was refused without being sent while the cool-down after one runs. `sec_unreachable`: SEC EDGAR gave no complete, readable response — on the last attempt made (the third, or an earlier one once this call's 40-second budget for SEC failures ran out) the connection failed, no response headers arrived within 15 seconds, or the body broke off or stalled for 15 seconds, each wait capped at what was left of that budget; a 200 body was not the JSON SEC serves; or earlier SEC failures had spent that budget, so the request was never sent. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive. `no_documents`: Filing index lists items but no fetchable primary document was found. `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return. `filing_not_found`: No filing matches the accession number under any candidate CIK. `offset_out_of_range`: The provided offset is at or beyond the end of the document. `section_not_found`: The section string matched no detected heading and no line of the document. `phrase_not_found`: No occurrence of the find phrase starts at or after offset: the document does not contain it, or holds it only before offset. `rate_limited`: SEC is rate-limiting this server's IP — SEC answered 429, or the call was refused without being sent while the cool-down after one runs. `sec_unreachable`: SEC EDGAR gave no complete, readable response — on the last attempt made (the third, or an earlier one once this call's 40-second budget for SEC failures ran out) the connection failed, no response headers arrived within 15 seconds, or the body broke off or stalled for 15 seconds, each wait capped at what was left of that budget; a 200 body was not the JSON SEC serves; or earlier SEC failures had spent that budget, so the request was never sent. `sec_unavailable`: SEC EDGAR answered HTTP 500, 502, 503, or 504 on the last attempt made (the third, or an earlier one once this call's 40-second budget for SEC failures ran out). Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "document_not_found",
      -  "no_documents",
      -  "binary_document",
      -  "filing_not_found",
      -  "offset_out_of_range",
      -  "section_not_found",
      -  "rate_limited",
      -  "sec_unreachable"
      -]New value: +[
      +  "document_not_found",
      +  "no_documents",
      +  "binary_document",
      +  "filing_not_found",
      +  "offset_out_of_range",
      +  "section_not_found",
      +  "phrase_not_found",
      +  "rate_limited",
      +  "sec_unreachable",
      +  "sec_unavailable"
      +]
    • changedOutput schema / properties / next_offset / description
      Previous value: -"Offset of the next page, to pass as offset without section; present while content_truncated is true."New value: +"Offset of the next page, to pass as offset without section or find; present while content_truncated is true."
    • changedOutput schema / properties / notice / description
      Previous value: -"How to read the next page, which file was read when the archive does not serve the indexed primary, when section landed on a document line rather than a detected heading, and how many headings were detected when the outline lists fewer."New value: +"How to read the next page or list more occurrences of find, which file was read when the archive does not serve the indexed primary, when section landed on a document line rather than a detected heading, and how many headings were detected when the outline lists fewer."
    • addedOutput schema / properties / occurrences
      Added value: +{
      +  "description": "With find: up to 20 occurrences, from the one the page opens at.",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One occurrence of find.",
      +    "properties": {
      +      "context": {
      +        "description": "The match and up to 40 characters either side, whitespace runs as one space.",
      +        "type": "string"
      +      },
      +      "offset": {
      +        "description": "Character offset where the occurrence starts.",
      +        "type": "number"
      +      }
      +    },
      +    "required": [
      +      "offset",
      +      "context"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / occurrences_total
      Added value: +{
      +  "description": "With find: occurrences in the whole document.",
      +  "type": "number"
      +}
    • changedOutput schema / properties / outline / description
      Previous value: -"Up to 50 detected headings, on the first page of a truncated response (offset=0, no section). Past 50, Item and Part headings come first (bare TOC copies of titled ones dropped), then the earliest others; the notice gives the detected count. Pass a heading offset as offset, or its text as section."New value: +"Up to 50 detected headings on a truncated first page (offset=0, no section or find). Past 50: Item and Part headings first (bare TOC copies of titled ones dropped), then the earliest; the notice gives the count. Pass text as section (a linked TOC row lands on its section) or offset as offset."
  2. Changed3 schema fields changed
    • changedInput schema / properties / cik / description
      Previous value: -"Company CIK, digits only (resolve via secedgar_company_search if you have a ticker or name). Optional but recommended — speeds up archive lookup. If omitted, likely filing CIKs are inferred from SEC search metadata and archive paths."New value: +"Filer CIK, digits only (resolve via secedgar_company_search if you have a ticker or name). Optional but recommended — speeds up archive lookup. If omitted, the filer is looked up from the accession number through EDGAR full-text search (2001 onward) and the accession number's own prefix, which for many filings is a filing agent's CIK, and when none of those directories serves the filing, through the filers its index page names."
    • changedInput schema / properties / document / description
      Previous value: -"Specific document filename within the filing (e.g., \"ex-21.htm\" for subsidiaries list). Default: the primary document. Available documents are listed in the response metadata under documents; entries marked binary hold no text and are rejected."New value: +"Specific document filename within the filing (e.g., \"ex-21.htm\" for subsidiaries list). Omitted or blank: the primary document. Available documents are listed in the response metadata under documents, and a primary_document value is accepted too; entries marked binary hold no text and are rejected."
    • changedOutput schema / properties / primary_document / description
      Previous value: -"Filename of the primary document. When the archive does not serve the one the index names (common in 2000–2001), this is the full submission file <accession>.txt instead; the notice names both."New value: +"Primary document as read: an XML form's SEC rendering (xsl…/form4.xml) up to 600 KB raw; a 2000–2001 name SEC does not serve, as <accession>-<name>, else the full submission <accession>.txt."
  3. Changed2 schema fields changed
    • changedInput schema / properties / content_limit / description
      Previous value: -"Maximum characters of document text to return per page. 10-K filings can exceed 500,000 characters; S-1/A can exceed 1,000,000. Default 50,000 captures ~12,000 words (typically business overview, risk factors, and MD&A). Increase to 200,000 for full financial statements, or decrease for quick summaries. Use offset or section for subsequent pages."New value: +"Maximum characters of document text to return per page. 10-K filings can exceed 500,000 characters; S-1/A can exceed 1,000,000. Default 50,000 captures ~12,000 words (typically business overview, risk factors, and MD&A). Increase to 200,000 for full financial statements, or decrease for quick summaries. Use offset or section for subsequent pages. Capped at 200000: a larger value, up to 1000000, returns what 200000 returns."
    • changedInput schema / properties / content_limit / maximum
      Previous value: -200000New value: +1000000
  4. Changed2 schema fields changed
    • changedInput schema / properties / section / description
      Previous value: -"Jump to a named section, matched against every detected heading and the document's own lines (e.g. 'risk factors', 'item 7', 'item 2.02', 'certain relationships'). The first match wins, in this order: a heading equal to the value, or whose title after its Item/Part marker equals it; the first Item or Part heading containing it; a document line equal to it — a subheading the outline omits ('Liquidity and Capital Resources'); the first other heading containing it; a document line starting with it. In a proxy statement (DEF 14A and its variants), whose ITEM headings are ballot proposals, the first heading of any kind containing the value comes before both document-line steps. Within each heading step a body heading wins over a table-of-contents row, which lands only when nothing else at that step matches. A line landing says so in the notice; table-of-contents rows and wrapped cross-references are never line landings. A leading 20-F sub-item label on a heading or line ('3D.', 'B.') is ignored, so 'risk factors' reaches '3D. RISK FACTORS'; the value itself is matched as given. A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16, and 'part i' never reaches Part II. Every step ignores case, whitespace, and quote style, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones; the steps comparing a whole heading or line (equal to, starting with) also ignore the punctuation between an Item or Part marker and its title, so 'Item 1A Risk Factors' reaches 'Item 1A. – Risk Factors'. Takes precedence over offset when both are provided, so leave it out when paging on with next_offset. On a miss, the error message includes the detected outline so you can pick the correct heading."New value: +"Jump to a named section, matched against every detected heading and the document's own lines (e.g. 'risk factors', 'item 7', 'item 2.02', 'certain relationships'). The first match wins, in this order: a heading equal to the value, or whose title after its Item/Part marker equals it; the first Item or Part heading containing it; a document line equal to it — a subheading the outline omits ('Liquidity and Capital Resources') — unless the line labels a table row; the first other heading containing it; a table-row label equal to it, else a document line starting with it. In a proxy statement (DEF 14A and its variants), whose ITEM headings are ballot proposals, the first heading of any kind containing the value comes before both document-line steps. Within each heading step a body heading wins over a table-of-contents row, which lands only when nothing else at that step matches. A line landing says so in the notice; table-of-contents rows and wrapped cross-references are never line landings. A leading 20-F sub-item label on a heading or line ('3D.', 'B.') is ignored, so 'risk factors' reaches '3D. RISK FACTORS'; the value itself is matched as given. A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16, and 'part i' never reaches Part II. Every step ignores case, whitespace, and quote style, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones; the steps comparing a whole heading or line (equal to, starting with) also ignore the punctuation between an Item or Part marker and its title, so 'Item 1A Risk Factors' reaches 'Item 1A. – Risk Factors'. Takes precedence over offset when both are provided, so leave it out when paging on with next_offset. On a miss, the error message includes the detected outline so you can pick the correct heading."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive. `no_documents`: Filing index lists items but no fetchable primary document was found. `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return. `filing_not_found`: No filing matches the accession number under any candidate CIK. `offset_out_of_range`: The provided offset is at or beyond the end of the document. `section_not_found`: The section string matched no detected heading and no line of the document. `rate_limited`: SEC is rate-limiting this server's IP — SEC answered 429, or the call was refused without being sent while the cool-down after one runs. `sec_unreachable`: The last of three attempts to reach SEC EDGAR got no HTTP response — the connection failed, or no response headers arrived within 15 seconds. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive. `no_documents`: Filing index lists items but no fetchable primary document was found. `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return. `filing_not_found`: No filing matches the accession number under any candidate CIK. `offset_out_of_range`: The provided offset is at or beyond the end of the document. `section_not_found`: The section string matched no detected heading and no line of the document. `rate_limited`: SEC is rate-limiting this server's IP — SEC answered 429, or the call was refused without being sent while the cool-down after one runs. `sec_unreachable`: SEC EDGAR gave no complete, readable response — on the last attempt made (the third, or an earlier one once this call's 40-second budget for SEC failures ran out) the connection failed, no response headers arrived within 15 seconds, or the body broke off or stalled for 15 seconds, each wait capped at what was left of that budget; a 200 body was not the JSON SEC serves; or earlier SEC failures had spent that budget, so the request was never sent. Other values are possible when a failure originates below the handler."
  5. Changed5 schema fields changed
    • changedInput schema / properties / offset / description
      Previous value: -"Character offset into the extracted document text. Pass next_offset from a truncated response to continue reading the next page. Default 0 reads from the beginning."New value: +"Character offset into the extracted document text. Pass next_offset from a truncated response to continue reading the next page, and leave section out: section takes precedence over offset. Default 0 reads from the beginning."
    • changedInput schema / properties / section / description
      Previous value: -"Jump to a named section, matched case-insensitively against every detected heading (e.g. 'risk factors', 'item 7', 'item 2.02', 'certain relationships'): a heading equal to the value, or whose title after its Item/Part marker equals it, wins first; otherwise the first heading containing it. A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16, and 'part i' never reaches Part II. With no heading match, a line of the document equal to the value, or else starting with it, is used — a subheading the outline omits ('Liquidity and Capital Resources') — and the notice says so; table-of-contents rows and wrapped cross-references are skipped. Matching also ignores whitespace and quote-style differences, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones. Takes precedence over offset when both are provided. On a miss, the error message includes the detected outline so you can pick the correct heading."New value: +"Jump to a named section, matched against every detected heading and the document's own lines (e.g. 'risk factors', 'item 7', 'item 2.02', 'certain relationships'). The first match wins, in this order: a heading equal to the value, or whose title after its Item/Part marker equals it; the first Item or Part heading containing it; a document line equal to it — a subheading the outline omits ('Liquidity and Capital Resources'); the first other heading containing it; a document line starting with it. In a proxy statement (DEF 14A and its variants), whose ITEM headings are ballot proposals, the first heading of any kind containing the value comes before both document-line steps. Within each heading step a body heading wins over a table-of-contents row, which lands only when nothing else at that step matches. A line landing says so in the notice; table-of-contents rows and wrapped cross-references are never line landings. A leading 20-F sub-item label on a heading or line ('3D.', 'B.') is ignored, so 'risk factors' reaches '3D. RISK FACTORS'; the value itself is matched as given. A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16, and 'part i' never reaches Part II. Every step ignores case, whitespace, and quote style, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones; the steps comparing a whole heading or line (equal to, starting with) also ignore the punctuation between an Item or Part marker and its title, so 'Item 1A Risk Factors' reaches 'Item 1A. – Risk Factors'. Takes precedence over offset when both are provided, so leave it out when paging on with next_offset. On a miss, the error message includes the detected outline so you can pick the correct heading."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive. `no_documents`: Filing index lists items but no fetchable primary document was found. `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return. `filing_not_found`: No filing matches the accession number under any candidate CIK. `offset_out_of_range`: The provided offset is at or beyond the end of the document. `section_not_found`: The section string matched no detected heading and no line of the document. `rate_limited`: SEC is rate-limiting this server's IP — SEC answered 429, or the call was refused without being sent while the cool-down after one runs. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive. `no_documents`: Filing index lists items but no fetchable primary document was found. `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return. `filing_not_found`: No filing matches the accession number under any candidate CIK. `offset_out_of_range`: The provided offset is at or beyond the end of the document. `section_not_found`: The section string matched no detected heading and no line of the document. `rate_limited`: SEC is rate-limiting this server's IP — SEC answered 429, or the call was refused without being sent while the cool-down after one runs. `sec_unreachable`: The last of three attempts to reach SEC EDGAR got no HTTP response — the connection failed, or no response headers arrived within 15 seconds. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "document_not_found",
      -  "no_documents",
      -  "binary_document",
      -  "filing_not_found",
      -  "offset_out_of_range",
      -  "section_not_found",
      -  "rate_limited"
      -]New value: +[
      +  "document_not_found",
      +  "no_documents",
      +  "binary_document",
      +  "filing_not_found",
      +  "offset_out_of_range",
      +  "section_not_found",
      +  "rate_limited",
      +  "sec_unreachable"
      +]
    • changedOutput schema / properties / next_offset / description
      Previous value: -"Offset of the next page, to pass as offset; present while content_truncated is true."New value: +"Offset of the next page, to pass as offset without section; present while content_truncated is true."
  6. Changed4 schema fields changed
    • changedInput schema / properties / section / description
      Previous value: -"Jump to a named section by case-insensitive substring match against detected headings (e.g. 'risk factors', 'item 7', 'certain relationships'). A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16. Matching also ignores whitespace and quote-style differences, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones. Takes precedence over offset when both are provided. On a miss, the error message includes the detected outline so you can pick the correct heading."New value: +"Jump to a named section, matched case-insensitively against every detected heading (e.g. 'risk factors', 'item 7', 'item 2.02', 'certain relationships'): a heading equal to the value, or whose title after its Item/Part marker equals it, wins first; otherwise the first heading containing it. A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16, and 'part i' never reaches Part II. With no heading match, a line of the document equal to the value, or else starting with it, is used — a subheading the outline omits ('Liquidity and Capital Resources') — and the notice says so; table-of-contents rows and wrapped cross-references are skipped. Matching also ignores whitespace and quote-style differences, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones. Takes precedence over offset when both are provided. On a miss, the error message includes the detected outline so you can pick the correct heading."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive. `no_documents`: Filing index lists items but no fetchable primary document was found. `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return. `filing_not_found`: No filing matches the accession number under any candidate CIK. `offset_out_of_range`: The provided offset is at or beyond the end of the document. `section_not_found`: The section string did not match any detected heading in the document. `rate_limited`: SEC is rate-limiting this server's IP — SEC answered 429, or the call was refused without being sent while the cool-down after one runs. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive. `no_documents`: Filing index lists items but no fetchable primary document was found. `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return. `filing_not_found`: No filing matches the accession number under any candidate CIK. `offset_out_of_range`: The provided offset is at or beyond the end of the document. `section_not_found`: The section string matched no detected heading and no line of the document. `rate_limited`: SEC is rate-limiting this server's IP — SEC answered 429, or the call was refused without being sent while the cool-down after one runs. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / notice / description
      Previous value: -"How to read the next page, and which file was read when the archive does not serve the indexed primary."New value: +"How to read the next page, which file was read when the archive does not serve the indexed primary, when section landed on a document line rather than a detected heading, and how many headings were detected when the outline lists fewer."
    • changedOutput schema / properties / outline / description
      Previous value: -"Up to 50 headings, on the first page of a truncated response (offset=0, no section); pass a heading offset as offset, or its text as section."New value: +"Up to 50 detected headings, on the first page of a truncated response (offset=0, no section). Past 50, Item and Part headings come first (bare TOC copies of titled ones dropped), then the earliest others; the notice gives the detected count. Pass a heading offset as offset, or its text as section."
  7. Changed27 schema fields changed
    • changedInput schema / properties / section / description
      Previous value: -"Jump to a named section by case-insensitive substring match against detected headings (e.g. 'risk factors', 'item 7', 'certain relationships'). Matching also ignores whitespace and quote-style differences, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones. Takes precedence over offset when both are provided. On a miss, the error message includes the detected outline so you can pick the correct heading."New value: +"Jump to a named section by case-insensitive substring match against detected headings (e.g. 'risk factors', 'item 7', 'certain relationships'). A value ending in a number matches only that number: 'item 1' reaches Item 1 and Item 1A, never Items 10–16. Matching also ignores whitespace and quote-style differences, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones. Takes precedence over offset when both are provided. On a miss, the error message includes the detected outline so you can pick the correct heading."
    • changedOutput schema / properties / content_total_length / description
      Previous value: -"Full document length before any truncation."New value: +"Full document length in characters."
    • changedOutput schema / properties / documents / description
      Previous value: -"Filing documents grouped by category. Every name is a valid document input EXCEPT entries carrying binary: true — scanned pages, PDFs, packaged archives and spreadsheets, which hold no text and are rejected with a binary_document error. Scans can outnumber readable documents in a filing, so read the flag before picking a name. XBRL viewer artifacts are suppressed by default; setting include_xbrl=true surfaces them under the xbrl bucket."New value: +"Filing documents by category. Any name is a valid document input except entries with binary: true, which fail with binary_document; scans can outnumber readable documents."
    • changedOutput schema / properties / documents / properties / auxiliary / description
      Previous value: -"Other supporting documents that aren't the primary, exhibits, or XBRL artifacts (cover pages, audit consent letters, embedded graphics)."New value: +"Other supporting documents: cover pages, consent letters, graphics."
    • changedOutput schema / properties / documents / properties / auxiliary / items / properties / binary / description
      Previous value: -"Present and true when the entry holds binary bytes — a scanned page or logo, a PDF exhibit, a packaged archive or spreadsheet. These cannot be converted to text and are rejected by the document input. Absent for readable entries."New value: +"True for a binary entry (scan, PDF, archive, spreadsheet); absent otherwise."
    • changedOutput schema / properties / documents / properties / auxiliary / items / properties / description / description
      Previous value: -"Human-readable description (e.g., \"Annual Report\", \"Subsidiaries of the Registrant\"). Absent when SEC published none for this entry."New value: +"SEC description (e.g., \"Subsidiaries of the Registrant\"). Absent when none."
    • changedOutput schema / properties / documents / properties / auxiliary / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), \"GRAPHIC\"/\"PDF\"/\"BINARY\" for known binary file extensions, and \"unknown\" for everything else."New value: +"SEC document type (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\"), or without a submission header a filename-inferred label (\"exhibit\", \"PDF\", \"unknown\")."
    • changedOutput schema / properties / documents / properties / exhibits / description
      Previous value: -"Filed exhibits (EX-21 subsidiaries, EX-31/32 certifications, EX-99 press releases, etc.). Excludes XBRL technical exhibits (EX-101.*). Identified by the EX- prefix on the document type, or by common exhibit filename patterns when the submission header is unavailable (type \"exhibit\"). Exhibits with unrecognizable filenames may still appear under auxiliary in the header-less case."New value: +"Filed exhibits (EX-21, EX-31/32, EX-99, etc.), excluding XBRL EX-101.*; without a submission header, matched by filename (type \"exhibit\"), the rest under auxiliary."
    • changedOutput schema / properties / documents / properties / exhibits / items / properties / binary / description
      Previous value: -"Present and true when the entry holds binary bytes — a scanned page or logo, a PDF exhibit, a packaged archive or spreadsheet. These cannot be converted to text and are rejected by the document input. Absent for readable entries."New value: +"True for a binary entry (scan, PDF, archive, spreadsheet); absent otherwise."
    • changedOutput schema / properties / documents / properties / exhibits / items / properties / description / description
      Previous value: -"Human-readable description (e.g., \"Annual Report\", \"Subsidiaries of the Registrant\"). Absent when SEC published none for this entry."New value: +"SEC description (e.g., \"Subsidiaries of the Registrant\"). Absent when none."
    • changedOutput schema / properties / documents / properties / exhibits / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), \"GRAPHIC\"/\"PDF\"/\"BINARY\" for known binary file extensions, and \"unknown\" for everything else."New value: +"SEC document type (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\"), or without a submission header a filename-inferred label (\"exhibit\", \"PDF\", \"unknown\")."
    • changedOutput schema / properties / documents / properties / primary / description
      Previous value: -"Primary filing document(s). Typically a single entry whose type matches the form (e.g., \"10-K\")."New value: +"Primary document(s), typically one entry whose type matches the form."
    • changedOutput schema / properties / documents / properties / primary / items / properties / binary / description
      Previous value: -"Present and true when the entry holds binary bytes — a scanned page or logo, a PDF exhibit, a packaged archive or spreadsheet. These cannot be converted to text and are rejected by the document input. Absent for readable entries."New value: +"True for a binary entry (scan, PDF, archive, spreadsheet); absent otherwise."
    • changedOutput schema / properties / documents / properties / primary / items / properties / description / description
      Previous value: -"Human-readable description (e.g., \"Annual Report\", \"Subsidiaries of the Registrant\"). Absent when SEC published none for this entry."New value: +"SEC description (e.g., \"Subsidiaries of the Registrant\"). Absent when none."
    • changedOutput schema / properties / documents / properties / primary / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), \"GRAPHIC\"/\"PDF\"/\"BINARY\" for known binary file extensions, and \"unknown\" for everything else."New value: +"SEC document type (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\"), or without a submission header a filename-inferred label (\"exhibit\", \"PDF\", \"unknown\")."
    • changedOutput schema / properties / documents / properties / xbrl / description
      Previous value: -"XBRL viewer artifacts and machine-readable taxonomy files. Only present when include_xbrl=true."New value: +"XBRL viewer artifacts and taxonomy files. Present only when include_xbrl=true."
    • changedOutput schema / properties / documents / properties / xbrl / items / properties / binary / description
      Previous value: -"Present and true when the entry holds binary bytes — a scanned page or logo, a PDF exhibit, a packaged archive or spreadsheet. These cannot be converted to text and are rejected by the document input. Absent for readable entries."New value: +"True for a binary entry (scan, PDF, archive, spreadsheet); absent otherwise."
    • changedOutput schema / properties / documents / properties / xbrl / items / properties / description / description
      Previous value: -"Human-readable description (e.g., \"Annual Report\", \"Subsidiaries of the Registrant\"). Absent when SEC published none for this entry."New value: +"SEC description (e.g., \"Subsidiaries of the Registrant\"). Absent when none."
    • changedOutput schema / properties / documents / properties / xbrl / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), \"GRAPHIC\"/\"PDF\"/\"BINARY\" for known binary file extensions, and \"unknown\" for everything else."New value: +"SEC document type (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\"), or without a submission header a filename-inferred label (\"exhibit\", \"PDF\", \"unknown\")."
    • changedOutput schema / properties / form / description
      Previous value: -"Form type (e.g., \"10-K\", \"10-Q\"). From the company's submissions feed for a recent filing, else from the filing's own SEC header. Absent only when neither source carries it."New value: +"Form type (e.g., \"10-K\"), from the submissions feed or the filing's SEC header. Absent only when neither has it."
    • changedOutput schema / properties / next_offset / description
      Previous value: -"Character offset to pass as offset on the next call to continue reading. Only present when the response was truncated. Calling agents should follow this until content_truncated is false."New value: +"Offset of the next page, to pass as offset; present while content_truncated is true."
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance on reading the next page when the content was capped."New value: +"How to read the next page, and which file was read when the archive does not serve the indexed primary."
    • changedOutput schema / properties / outline / description
      Previous value: -"Document outline — up to 50 detected headings with their character offsets. Present on the first page of a truncated response (offset=0, no section). Use a heading offset as offset, or pass heading text as section, to jump to that section."New value: +"Up to 50 headings, on the first page of a truncated response (offset=0, no section); pass a heading offset as offset, or its text as section."
    • changedOutput schema / properties / outline / items / properties / offset / description
      Previous value: -"Character offset of this heading in the full document. Pass as offset to jump directly to this section."New value: +"Character offset of this heading in the full document; pass as offset."
    • changedOutput schema / properties / period_ending / description
      Previous value: -"Period the filing reports on (YYYY-MM-DD), from the same source as form. Absent for forms with no period of report (S-8, Form 4, proxy statements) and when neither source carries it."New value: +"Period of report (YYYY-MM-DD), from the same source as form. Absent for forms without one (S-8, Form 4, proxy statements) or when neither source has it."
    • changedOutput schema / properties / primary_document / description
      Previous value: -"Filename of the filing's actual primary document (e.g., the 10-K HTML file)."New value: +"Filename of the primary document. When the archive does not serve the one the index names (common in 2000–2001), this is the full submission file <accession>.txt instead; the notice names both."
    • changedOutput schema / properties / requested_document / description
      Previous value: -"Filename of the specific document requested via the document param. Only present when document differs from primary_document."New value: +"Filename requested via document. Present only when it differs from primary_document."
  8. Changed2 schema fields changed
    • changedOutput schema / properties / form / description
      Previous value: -"Form type (e.g., \"10-K\", \"10-Q\"). Absent for filings older than the last ~1,000 the company has filed (SEC does not surface metadata for those without a separate fetch)."New value: +"Form type (e.g., \"10-K\", \"10-Q\"). From the company's submissions feed for a recent filing, else from the filing's own SEC header. Absent only when neither source carries it."
    • changedOutput schema / properties / period_ending / description
      Previous value: -"Period the filing reports on (YYYY-MM-DD). Absent under the same conditions as form."New value: +"Period the filing reports on (YYYY-MM-DD), from the same source as form. Absent for forms with no period of report (S-8, Form 4, proxy statements) and when neither source carries it."
  9. Changed2 schema fields changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive `no_documents`: Filing index lists items but no fetchable primary document was found `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return `filing_not_found`: No filing matches the accession number under any candidate CIK `offset_out_of_range`: The provided offset is at or beyond the end of the document `section_not_found`: The section string did not match any detected heading in the document Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive. `no_documents`: Filing index lists items but no fetchable primary document was found. `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return. `filing_not_found`: No filing matches the accession number under any candidate CIK. `offset_out_of_range`: The provided offset is at or beyond the end of the document. `section_not_found`: The section string did not match any detected heading in the document. `rate_limited`: SEC is rate-limiting this server's IP — SEC answered 429, or the call was refused without being sent while the cool-down after one runs. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "document_not_found",
      -  "no_documents",
      -  "binary_document",
      -  "filing_not_found",
      -  "offset_out_of_range",
      -  "section_not_found"
      -]New value: +[
      +  "document_not_found",
      +  "no_documents",
      +  "binary_document",
      +  "filing_not_found",
      +  "offset_out_of_range",
      +  "section_not_found",
      +  "rate_limited"
      +]
  10. Changed1 schema field changed
    • changedInput schema / properties / section / description
      Previous value: -"Jump to a named section by case-insensitive substring match against detected headings (e.g. 'risk factors', 'item 7', 'certain relationships'). Takes precedence over offset when both are provided. On a miss, the error message includes the detected outline so you can pick the correct heading."New value: +"Jump to a named section by case-insensitive substring match against detected headings (e.g. 'risk factors', 'item 7', 'certain relationships'). Matching also ignores whitespace and quote-style differences, so a heading copied from the outline resolves whether it carries the filing's non-breaking spaces and curly quotes or plain ones. Takes precedence over offset when both are provided. On a miss, the error message includes the detected outline so you can pick the correct heading."
  11. Changed11 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "accession_number",
      +      "cik",
      +      "primary_document",
      +      "documents",
      +      "content",
      +      "content_truncated",
      +      "content_total_length",
      +      "filing_url"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / cap
      Added value: +{
      +  "description": "The `content_limit` that was applied.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / error
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Present when the call failed. Absent on success.",
      +  "properties": {
      +    "code": {
      +      "description": "JSON-RPC error code for this failure.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "data": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "reason": {
      +          "description": "Machine-readable failure mode. Declared by this tool: `document_not_found`: A specific document was requested but not present in the filing archive `no_documents`: Filing index lists items but no fetchable primary document was found `binary_document`: The requested document is a binary entry (scanned image, PDF, archive) with no text to return `filing_not_found`: No filing matches the accession number under any candidate CIK `offset_out_of_range`: The provided offset is at or beyond the end of the document `section_not_found`: The section string did not match any detected heading in the document Other values are possible when a failure originates below the handler.",
      +          "examples": [
      +            "document_not_found",
      +            "no_documents",
      +            "binary_document",
      +            "filing_not_found",
      +            "offset_out_of_range",
      +            "section_not_found"
      +          ],
      +          "type": "string"
      +        },
      +        "recovery": {
      +          "additionalProperties": {},
      +          "description": "Actionable next step for the caller.",
      +          "properties": {
      +            "hint": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "hint"
      +          ],
      +          "type": "object"
      +        },
      +        "retryable": {
      +          "description": "Whether retrying may succeed.",
      +          "type": "boolean"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "message": {
      +      "description": "Human-readable description of what went wrong.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "code",
      +    "message"
      +  ],
      +  "type": "object"
      +}
    • addedOutput schema / properties / notice
      Added value: +{
      +  "description": "Guidance on reading the next page when the content was capped.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / outline / description
      Previous value: -"Document outline — detected headings with their character offsets. Present on the first page of a truncated response (offset=0, no section). Use a heading offset as offset, or pass heading text as section, to jump to that section."New value: +"Document outline — up to 50 detected headings with their character offsets. Present on the first page of a truncated response (offset=0, no section). Use a heading offset as offset, or pass heading text as section, to jump to that section."
    • addedOutput schema / properties / shown
      Added value: +{
      +  "description": "Characters of document text returned on this page.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / truncated
      Added value: +{
      +  "description": "True when the document is longer than `content_limit` allowed through.",
      +  "type": "boolean"
      +}
    • removedOutput schema / required
      Removed value: -[
      -  "accession_number",
      -  "cik",
      -  "primary_document",
      -  "documents",
      -  "content",
      -  "content_truncated",
      -  "content_total_length",
      -  "filing_url"
      -]
  12. Changed10 schema fields changed
    • changedInput schema / properties / document / description
      Previous value: -"Specific document filename within the filing (e.g., \"ex-21.htm\" for subsidiaries list). Default: the primary document. Available documents listed in the response metadata."New value: +"Specific document filename within the filing (e.g., \"ex-21.htm\" for subsidiaries list). Default: the primary document. Available documents are listed in the response metadata under documents; entries marked binary hold no text and are rejected."
    • changedOutput schema / properties / documents / description
      Previous value: -"Filing documents grouped by category. Names from any list are valid values for the document input. XBRL viewer artifacts are suppressed by default; setting include_xbrl=true surfaces them under the xbrl bucket."New value: +"Filing documents grouped by category. Every name is a valid document input EXCEPT entries carrying binary: true — scanned pages, PDFs, packaged archives and spreadsheets, which hold no text and are rejected with a binary_document error. Scans can outnumber readable documents in a filing, so read the flag before picking a name. XBRL viewer artifacts are suppressed by default; setting include_xbrl=true surfaces them under the xbrl bucket."
    • addedOutput schema / properties / documents / properties / auxiliary / items / properties / binary
      Added value: +{
      +  "description": "Present and true when the entry holds binary bytes — a scanned page or logo, a PDF exhibit, a packaged archive or spreadsheet. These cannot be converted to text and are rejected by the document input. Absent for readable entries.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / documents / properties / auxiliary / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), \"GRAPHIC\"/\"PDF\"/\"BINARY\" for known binary file extensions, and \"unknown\" for everything else."
    • addedOutput schema / properties / documents / properties / exhibits / items / properties / binary
      Added value: +{
      +  "description": "Present and true when the entry holds binary bytes — a scanned page or logo, a PDF exhibit, a packaged archive or spreadsheet. These cannot be converted to text and are rejected by the document input. Absent for readable entries.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / documents / properties / exhibits / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), \"GRAPHIC\"/\"PDF\"/\"BINARY\" for known binary file extensions, and \"unknown\" for everything else."
    • addedOutput schema / properties / documents / properties / primary / items / properties / binary
      Added value: +{
      +  "description": "Present and true when the entry holds binary bytes — a scanned page or logo, a PDF exhibit, a packaged archive or spreadsheet. These cannot be converted to text and are rejected by the document input. Absent for readable entries.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / documents / properties / primary / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), \"GRAPHIC\"/\"PDF\"/\"BINARY\" for known binary file extensions, and \"unknown\" for everything else."
    • addedOutput schema / properties / documents / properties / xbrl / items / properties / binary
      Added value: +{
      +  "description": "Present and true when the entry holds binary bytes — a scanned page or logo, a PDF exhibit, a packaged archive or spreadsheet. These cannot be converted to text and are rejected by the document input. Absent for readable entries.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / documents / properties / xbrl / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), \"GRAPHIC\"/\"PDF\"/\"BINARY\" for known binary file extensions, and \"unknown\" for everything else."
  13. Changed1 schema field changed
    • changedInput schema / properties / section / description
      Previous value: -"Jump to a named section by case-insensitive substring match against detected headings (e.g. 'risk factors', 'item 7', 'certain relationships'). Takes precedence over offset when both are provided. On a miss, the error data carries the detected outline so you can pick the correct heading."New value: +"Jump to a named section by case-insensitive substring match against detected headings (e.g. 'risk factors', 'item 7', 'certain relationships'). Takes precedence over offset when both are provided. On a miss, the error message includes the detected outline so you can pick the correct heading."
  14. Changed8 schema fields changed
    • addedInput schema / properties / accession_number / pattern
      Added value: +"^(?:\\d{10}-\\d{2}-\\d{6}|\\d{18})$"
    • changedInput schema / properties / cik / description
      Previous value: -"Company CIK (resolve via secedgar_company_search if you have a ticker or name). Optional but recommended — speeds up archive lookup. If omitted, likely filing CIKs are inferred from SEC search metadata and archive paths."New value: +"Company CIK, digits only (resolve via secedgar_company_search if you have a ticker or name). Optional but recommended — speeds up archive lookup. If omitted, likely filing CIKs are inferred from SEC search metadata and archive paths."
    • addedInput schema / properties / cik / pattern
      Added value: +"^\\d{1,10}$"
    • changedOutput schema / properties / documents / properties / auxiliary / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), and \"unknown\" for everything else."
    • changedOutput schema / properties / documents / properties / exhibits / description
      Previous value: -"Filed exhibits (EX-21 subsidiaries, EX-31/32 certifications, EX-99 press releases, etc.). Excludes XBRL technical exhibits (EX-101.*). Identified by the EX- prefix on the document type. Some exhibits may appear under auxiliary when the submission header is unavailable and the filename has no recognizable pattern."New value: +"Filed exhibits (EX-21 subsidiaries, EX-31/32 certifications, EX-99 press releases, etc.). Excludes XBRL technical exhibits (EX-101.*). Identified by the EX- prefix on the document type, or by common exhibit filename patterns when the submission header is unavailable (type \"exhibit\"). Exhibits with unrecognizable filenames may still appear under auxiliary in the header-less case."
    • changedOutput schema / properties / documents / properties / exhibits / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), and \"unknown\" for everything else."
    • changedOutput schema / properties / documents / properties / primary / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), and \"unknown\" for everything else."
    • changedOutput schema / properties / documents / properties / xbrl / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename: known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.), \"exhibit\" for common exhibit filename patterns (ex-21.htm, exhibit21, dex991), and \"unknown\" for everything else."
  15. Changed8 schema fields changed
    • changedInput schema / properties / content_limit / description
      Previous value: -"Maximum characters of document text to return. 10-K filings can exceed 500,000 characters. Default 50,000 captures ~12,000 words (typically business overview, risk factors, and MD&A). Increase to 200,000 for full financial statements, or decrease for quick summaries."New value: +"Maximum characters of document text to return per page. 10-K filings can exceed 500,000 characters; S-1/A can exceed 1,000,000. Default 50,000 captures ~12,000 words (typically business overview, risk factors, and MD&A). Increase to 200,000 for full financial statements, or decrease for quick summaries. Use offset or section for subsequent pages."
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "description": "Character offset into the extracted document text. Pass next_offset from a truncated response to continue reading the next page. Default 0 reads from the beginning.",
      +  "maximum": 9007199254740991,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedInput schema / properties / section
      Added value: +{
      +  "description": "Jump to a named section by case-insensitive substring match against detected headings (e.g. 'risk factors', 'item 7', 'certain relationships'). Takes precedence over offset when both are provided. On a miss, the error data carries the detected outline so you can pick the correct heading.",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • changedOutput schema / properties / content / description
      Previous value: -"Document text content, truncated to content_limit."New value: +"Document text content for this page window."
    • changedOutput schema / properties / content_total_length / description
      Previous value: -"Full document length before truncation."New value: +"Full document length before any truncation."
    • changedOutput schema / properties / content_truncated / description
      Previous value: -"True if content was truncated."New value: +"True if content was truncated at content_limit."
    • addedOutput schema / properties / next_offset
      Added value: +{
      +  "description": "Character offset to pass as offset on the next call to continue reading. Only present when the response was truncated. Calling agents should follow this until content_truncated is false.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / outline
      Added value: +{
      +  "description": "Document outline — detected headings with their character offsets. Present on the first page of a truncated response (offset=0, no section). Use a heading offset as offset, or pass heading text as section, to jump to that section.",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One detected heading with its offset.",
      +    "properties": {
      +      "heading": {
      +        "description": "Detected heading text.",
      +        "type": "string"
      +      },
      +      "offset": {
      +        "description": "Character offset of this heading in the full document. Pass as offset to jump directly to this section.",
      +        "type": "number"
      +      }
      +    },
      +    "required": [
      +      "heading",
      +      "offset"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  16. Changed2 schema fields changed
    • changedOutput schema / properties / primary_document / description
      Previous value: -"Filename of the document whose text was returned in content."New value: +"Filename of the filing's actual primary document (e.g., the 10-K HTML file)."
    • addedOutput schema / properties / requested_document
      Added value: +{
      +  "description": "Filename of the specific document requested via the document param. Only present when document differs from primary_document.",
      +  "type": "string"
      +}
  17. Changed6 schema fields changed
    • changedOutput schema / properties / documents / description
      Previous value: -"Filing documents grouped by category. Pass a name from any list as the document input param to fetch that file. XBRL viewer artifacts are suppressed by default — set include_xbrl=true to surface them under the xbrl bucket."New value: +"Filing documents grouped by category. Names from any list are valid values for the document input. XBRL viewer artifacts are suppressed by default; setting include_xbrl=true surfaces them under the xbrl bucket."
    • changedOutput schema / properties / documents / properties / auxiliary / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the header file is unavailable, falls back to a name-pattern synthetic label for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."
    • changedOutput schema / properties / documents / properties / exhibits / description
      Previous value: -"Filed exhibits (EX-21 subsidiaries, EX-31/32 certifications, EX-99 press releases, etc.). Excludes XBRL technical exhibits (EX-101.*). Identified by the EX- prefix on the header TYPE — when the submission header is unavailable, exhibits whose filename does not match a known pattern fall through to auxiliary instead."New value: +"Filed exhibits (EX-21 subsidiaries, EX-31/32 certifications, EX-99 press releases, etc.). Excludes XBRL technical exhibits (EX-101.*). Identified by the EX- prefix on the document type. Some exhibits may appear under auxiliary when the submission header is unavailable and the filename has no recognizable pattern."
    • changedOutput schema / properties / documents / properties / exhibits / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the header file is unavailable, falls back to a name-pattern synthetic label for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."
    • changedOutput schema / properties / documents / properties / primary / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the header file is unavailable, falls back to a name-pattern synthetic label for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."
    • changedOutput schema / properties / documents / properties / xbrl / items / properties / type / description
      Previous value: -"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the header file is unavailable, falls back to a name-pattern synthetic label for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."New value: +"SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the submission header is unavailable, falls back to a label inferred from the filename for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else."
  18. Changed15 schema fields changed
    • changedInput schema / properties / cik / description
      Previous value: -"Company CIK. Optional but recommended — speeds up archive lookup. If omitted, the server resolves likely filing CIKs from SEC search metadata and archive paths."New value: +"Company CIK (resolve via secedgar_company_search if you have a ticker or name). Optional but recommended — speeds up archive lookup. If omitted, likely filing CIKs are inferred from SEC search metadata and archive paths."
    • addedInput schema / properties / include_xbrl
      Added value: +{
      +  "default": false,
      +  "description": "Include XBRL viewer artifacts and machine-readable taxonomy files (R*.htm fragments, *_cal/_def/_lab/_pre.xml linkbases, *_htm.xml inline instance, *.xsd schemas, MetaLinks.json, FilingSummary.xml, Show.js, report.css, *-xbrl.zip, Financial_Report.xlsx, EX-101.* technical exhibits) under documents.xbrl. Off by default — these dominate filing indexes (~100 entries on a typical 10-K) and are rarely relevant when reading filing content.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / accession_number / description
      Previous value: -"Filing accession number."New value: +"Filing accession number, normalized to dash format."
    • changedOutput schema / properties / cik / description
      Previous value: -"Company CIK."New value: +"Filing entity CIK, zero-padded to 10 digits."
    • changedOutput schema / properties / company_name / description
      Previous value: -"Filing entity name, if the CIK resolved to a known entity."New value: +"Filing entity name. Absent if the CIK did not resolve to a known entity."
    • addedOutput schema / properties / documents / additionalProperties
      Added value: +false
    • changedOutput schema / properties / documents / description
      Previous value: -"All documents in this filing. Use the name field with the document input param to fetch exhibits."New value: +"Filing documents grouped by category. Pass a name from any list as the document input param to fetch that file. XBRL viewer artifacts are suppressed by default — set include_xbrl=true to surface them under the xbrl bucket."
    • removedOutput schema / properties / documents / items
      Removed value: -{
      -  "additionalProperties": false,
      -  "description": "One document entry from the filing archive index.",
      -  "properties": {
      -    "name": {
      -      "description": "Document filename.",
      -      "type": "string"
      -    },
      -    "size": {
      -      "description": "File size in bytes.",
      -      "type": "number"
      -    },
      -    "type": {
      -      "description": "Document type.",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "name",
      -    "type"
      -  ],
      -  "type": "object"
      -}
    • addedOutput schema / properties / documents / properties
      Added value: +{
      +  "auxiliary": {
      +    "description": "Other supporting documents that aren't the primary, exhibits, or XBRL artifacts (cover pages, audit consent letters, embedded graphics).",
      +    "items": {
      +      "additionalProperties": false,
      +      "description": "One document entry from the filing.",
      +      "properties": {
      +        "description": {
      +          "description": "Human-readable description (e.g., \"Annual Report\", \"Subsidiaries of the Registrant\"). Absent when SEC published none for this entry.",
      +          "type": "string"
      +        },
      +        "name": {
      +          "description": "Document filename within the filing archive.",
      +          "type": "string"
      +        },
      +        "size": {
      +          "description": "File size in bytes.",
      +          "type": "number"
      +        },
      +        "type": {
      +          "description": "SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the header file is unavailable, falls back to a name-pattern synthetic label for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else.",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "name",
      +        "type"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  "exhibits": {
      +    "description": "Filed exhibits (EX-21 subsidiaries, EX-31/32 certifications, EX-99 press releases, etc.). Excludes XBRL technical exhibits (EX-101.*). Identified by the EX- prefix on the header TYPE — when the submission header is unavailable, exhibits whose filename does not match a known pattern fall through to auxiliary instead.",
      +    "items": {
      +      "additionalProperties": false,
      +      "description": "One document entry from the filing.",
      +      "properties": {
      +        "description": {
      +          "description": "Human-readable description (e.g., \"Annual Report\", \"Subsidiaries of the Registrant\"). Absent when SEC published none for this entry.",
      +          "type": "string"
      +        },
      +        "name": {
      +          "description": "Document filename within the filing archive.",
      +          "type": "string"
      +        },
      +        "size": {
      +          "description": "File size in bytes.",
      +          "type": "number"
      +        },
      +        "type": {
      +          "description": "SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the header file is unavailable, falls back to a name-pattern synthetic label for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else.",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "name",
      +        "type"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  "primary": {
      +    "description": "Primary filing document(s). Typically a single entry whose type matches the form (e.g., \"10-K\").",
      +    "items": {
      +      "additionalProperties": false,
      +      "description": "One document entry from the filing.",
      +      "properties": {
      +        "description": {
      +          "description": "Human-readable description (e.g., \"Annual Report\", \"Subsidiaries of the Registrant\"). Absent when SEC published none for this entry.",
      +          "type": "string"
      +        },
      +        "name": {
      +          "description": "Document filename within the filing archive.",
      +          "type": "string"
      +        },
      +        "size": {
      +          "description": "File size in bytes.",
      +          "type": "number"
      +        },
      +        "type": {
      +          "description": "SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the header file is unavailable, falls back to a name-pattern synthetic label for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else.",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "name",
      +        "type"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  "xbrl": {
      +    "description": "XBRL viewer artifacts and machine-readable taxonomy files. Only present when include_xbrl=true.",
      +    "items": {
      +      "additionalProperties": false,
      +      "description": "One document entry from the filing.",
      +      "properties": {
      +        "description": {
      +          "description": "Human-readable description (e.g., \"Annual Report\", \"Subsidiaries of the Registrant\"). Absent when SEC published none for this entry.",
      +          "type": "string"
      +        },
      +        "name": {
      +          "description": "Document filename within the filing archive.",
      +          "type": "string"
      +        },
      +        "size": {
      +          "description": "File size in bytes.",
      +          "type": "number"
      +        },
      +        "type": {
      +          "description": "SEC document type from the submission header (e.g., \"10-K\", \"EX-21.1\", \"GRAPHIC\", \"XML\"). When the header file is unavailable, falls back to a name-pattern synthetic label for known XBRL artifacts (\"XBRL-LINKBASE\", \"XBRL-INSTANCE\", etc.) and \"unknown\" for everything else.",
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "name",
      +        "type"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  }
      +}
    • addedOutput schema / properties / documents / required
      Added value: +[
      +  "primary",
      +  "exhibits",
      +  "auxiliary"
      +]
    • changedOutput schema / properties / documents / type
      Previous value: -"array"New value: +"object"
    • changedOutput schema / properties / filing_date / description
      Previous value: -"Date filed. Omitted when the filing predates the recent-submissions window."New value: +"Date the filing was submitted (YYYY-MM-DD). Absent under the same conditions as form."
    • changedOutput schema / properties / form / description
      Previous value: -"Form type. Omitted when the filing predates the recent-submissions window."New value: +"Form type (e.g., \"10-K\", \"10-Q\"). Absent for filings older than the last ~1,000 the company has filed (SEC does not surface metadata for those without a separate fetch)."
    • changedOutput schema / properties / period_ending / description
      Previous value: -"Period of report."New value: +"Period the filing reports on (YYYY-MM-DD). Absent under the same conditions as form."
    • changedOutput schema / properties / primary_document / description
      Previous value: -"Primary document filename."New value: +"Filename of the document whose text was returned in content."
  19. Changed1 schema field changed
    • addedOutput schema / properties / documents / items / description
      Added value: +"One document entry from the filing archive index."
  20. Changed5 schema fields changed
    • changedInput schema / properties / cik / description
      Previous value: -"Company CIK. Optional but recommended — speeds up URL construction. If omitted, derived from the accession number prefix."New value: +"Company CIK. Optional but recommended — speeds up archive lookup. If omitted, the server resolves likely filing CIKs from SEC search metadata and archive paths."
    • changedOutput schema / properties / company_name / description
      Previous value: -"Filing entity name."New value: +"Filing entity name, if the CIK resolved to a known entity."
    • changedOutput schema / properties / filing_date / description
      Previous value: -"Date filed."New value: +"Date filed. Omitted when the filing predates the recent-submissions window."
    • changedOutput schema / properties / form / description
      Previous value: -"Form type."New value: +"Form type. Omitted when the filing predates the recent-submissions window."
    • changedOutput schema / required
      Previous value: -[
      -  "accession_number",
      -  "form",
      -  "filing_date",
      -  "company_name",
      -  "cik",
      -  "primary_document",
      -  "documents",
      -  "content",
      -  "content_truncated",
      -  "content_total_length",
      -  "filing_url"
      -]New value: +[
      +  "accession_number",
      +  "cik",
      +  "primary_document",
      +  "documents",
      +  "content",
      +  "content_truncated",
      +  "content_total_length",
      +  "filing_url"
      +]
  21. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld, so the bar is lower, yet the description adds real operational context: responses get truncated and carry a next_offset, a miss on section returns the detected outline in the error, binary documents are rejected, and XBRL artifacts are hidden by default because they flood indexes. It also discloses the 200,000-character effective cap on content_limit, which materially changes how an agent should page.

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

Conciseness4/5

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

Four sentences, each load-bearing, with the fetch-and-return statement first and the paging modes after. Density is high but appropriate for eight parameters; the only slack is minor repetition of paging/precedence details the schema already states.

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

Completeness5/5

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

For a large-document reader with an output schema covering the return payload, the description covers everything an agent needs to call it correctly: identifier format source, truncation and resumption, section/find alternatives, and the content_limit sizing heuristic with concrete magnitudes. The one wart is the content_limit cap, which the schema advertises as 1,000,000 but the description says returns only 200,000 worth — consistent with the description's own text, though it makes the schema's maximum misleading.

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

Parameters4/5

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

The cross-parameter precedence rules (section over find over offset, find uses offset as a search start, leave section/find out when resuming from next_offset) are the genuinely valuable addition and are front-loaded rather than buried. Much of it is also present in the 100%-covered schema descriptions, so this is closer to a well-organized summary than net-new semantics.

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

Purpose5/5

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

Opens with a specific verb+resource ('Fetch a specific filing's metadata and document content by accession number') and states what is returned ('the primary document as readable text'). The scope is narrow enough (one filing, by accession number) that an agent can distinguish it from secedgar_search_filings or secedgar_get_financials without opening the schema.

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

Usage Guidelines4/5

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

Gives explicit conditional guidance among its own access modes: use offset/next_offset to page, section to jump to a heading, find to locate a phrase, and it names when an alternative mode applies ('For a phrase in the text that is not a heading, use find'). What it lacks is tool-level routing — it never says when to fetch a filing this way versus going through secedgar_search_filings or a specialized extractor, which is left to the sibling schemas.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.