Skip to main content
Glama

FinBridge

Explore Korean Disclosure Document (DART)

get_dart_document
Read-only

Explore one DART filing by receipt number while preserving section and table structure — the main body by default, or one of its attachments (audit reports carry the consolidated statements; the main body carries the business description).

Use get_dart_filings first to obtain rcept_no. Start with action='overview', then select a section or table instead of requesting a long flattened filing. The overview lists the archive's entries (main body + attachments with their first heading); pass entry='' to explore an attachment.

Args:

  • rcept_no: 14-digit DART receipt number

  • entry: archive entry name from the overview's entries list (default: the main body)

  • action: overview (default) | section | table | compare_tables | compare_sections

  • compare_rcept_no and compare_index: second filing and its selected table/section index for comparison; table_index/section_index selects the first. Use both overviews first. Only selected content is compared, not entire filings.

  • section_index or section_query: one section selector for action='section'

  • table_index: 1-based table selector for action='table'

  • max_chars: section text cap, 1,000-100,000 (default 30,000)

  • max_rows/max_columns: selected table caps (defaults 50/30)

  • overview_offset/overview_limit: paginate both section and table summaries with the same 0-based slice (defaults 0/20, max 100)

  • response_format: markdown or json

Returns source evidence for the OpenDART document entry and character range. Tables retain row/column order, cell text, rowspan/colspan and nearby reported unit labels. Zero and negative strings are not discarded. Separate HWP/PDF files are not fetched or rehosted.

This tool does not claim an XBRL presentation/calculation hierarchy. Use get_dart_financials for normalized figures, reported account groups and known statement sum checks.

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": {
      "rcept_no": "<rcept_no>"
    },
    "name": "get_dart_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
entryNoArchive entry to explore, exactly as the overview's entries list names it (e.g. 20260313001021_00761.xml for a consolidated audit report). Omit for the main body. Attachments are read from DART, not from the preserved copy.
freshNofalse (default): read FinBridge's preserved copy of this filing when we hold one, and DART otherwise. true: fetch the current version from DART now — use only when the user asks for the latest text or suspects a correction.
actionNoStart with the outline, then select a section or a leaf table.overview
max_rowsNoMaximum selected table rows; original row count is retained.
rcept_noYes14-digit DART receipt number from get_dart_filings
max_charsNoMaximum characters of selected section text; truncation is explicit.
max_columnsNoMaximum selected table columns; original column count is retained.
table_indexNo1-based leaf-table number; required for table action.
compare_indexNoTable or section index inside the second filing. Read that filing's overview first; table_index/section_index selects the first filing's side.
section_indexNo1-based section number from the outline; use only with section action.
section_queryNoSection title search; use instead of section_index. Ambiguous matches are rejected.
overview_limitNoMaximum section and table summaries per outline page; follow next_offset.
overview_offsetNo0-based outline slice offset for both sections and tables.
response_formatNoReadable markdown or JSON; both retain structured content.markdown
compare_rcept_noNoSecond filing's 14-digit receipt number, for compare_tables / compare_sections. The first filing is rcept_no.

Output Schema

NameRequiredDescriptionDefault
notesNo
tableNo
actionYes
tablesNo
sectionNo
overviewNo
sectionsNo
allowanceNo
comparisonNo
data_as_ofNo
preservationNo
source_evidenceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / section_index / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / table_index / maximum
      Added value: +9007199254740991
    • changedOutput schema / properties / allowance / additionalProperties
      Previous value: -trueNew value: +{}
    • changedOutput schema / properties / comparison / additionalProperties
      Previous value: -trueNew value: +{}
    • changedOutput schema / properties / data_as_of / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": true,
      -    "properties": {},
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": {},
      +    "properties": {},
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedOutput schema / properties / overview / additionalProperties
      Previous value: -trueNew value: +{}
    • changedOutput schema / properties / preservation / additionalProperties
      Previous value: -trueNew value: +{}
    • changedOutput schema / properties / section / additionalProperties
      Previous value: -trueNew value: +{}
    • changedOutput schema / properties / sections / items / additionalProperties
      Previous value: -trueNew value: +{}
    • changedOutput schema / properties / source_evidence / additionalProperties
      Previous value: -trueNew value: +{}
    • changedOutput schema / properties / table / additionalProperties
      Previous value: -trueNew value: +{}
    • changedOutput schema / properties / tables / items / additionalProperties
      Previous value: -trueNew value: +{}
  2. Changed1 schema field changed
    • addedOutput schema / properties / data_as_of
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": true,
      +      "properties": {},
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ]
      +}
  3. Changed1 schema field changed
    • addedOutput schema / properties / allowance
      Added value: +{
      +  "additionalProperties": true,
      +  "properties": {},
      +  "type": "object"
      +}
  4. Changed3 schema fields changed
    • addedInput schema / properties / entry / maxLength
      Added value: +120
    • addedInput schema / properties / entry / minLength
      Added value: +1
    • removedInput schema / properties / entry / pattern
      Removed value: -"^[\\p{L}\\p{N}._/-]{1,120}$"
  5. Changed1 schema field changed
    • addedInput schema / properties / entry
      Added value: +{
      +  "description": "Archive entry to explore, exactly as the overview's entries list names it (e.g. 20260313001021_00761.xml for a consolidated audit report). Omit for the main body. Attachments are read from DART, not from the preserved copy.",
      +  "pattern": "^[\\p{L}\\p{N}._/-]{1,120}$",
      +  "type": "string"
      +}
  6. Changed1 schema field changed
    • addedInput schema / properties / fresh
      Added value: +{
      +  "default": false,
      +  "description": "false (default): read FinBridge's preserved copy of this filing when we hold one, and DART otherwise. true: fetch the current version from DART now — use only when the user asks for the latest text or suspects a correction.",
      +  "type": "boolean"
      +}
  7. Changed2 schema fields changed
    • addedInput schema / properties / compare_index / description
      Added value: +"Table or section index inside the second filing. Read that filing's overview first; table_index/section_index selects the first filing's side."
    • addedInput schema / properties / compare_rcept_no / description
      Added value: +"Second filing's 14-digit receipt number, for compare_tables / compare_sections. The first filing is rcept_no."
  8. Changed6 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "overview",
      -  "section",
      -  "table"
      -]New value: +[
      +  "overview",
      +  "section",
      +  "table",
      +  "compare_tables",
      +  "compare_sections"
      +]
    • addedInput schema / properties / compare_index
      Added value: +{
      +  "exclusiveMinimum": 0,
      +  "maximum": 10000,
      +  "type": "integer"
      +}
    • addedInput schema / properties / compare_rcept_no
      Added value: +{
      +  "pattern": "^\\d{14}$",
      +  "type": "string"
      +}
    • changedOutput schema / properties / action / enum
      Previous value: -[
      -  "overview",
      -  "section",
      -  "table"
      -]New value: +[
      +  "overview",
      +  "section",
      +  "table",
      +  "compare_tables",
      +  "compare_sections"
      +]
    • addedOutput schema / properties / comparison
      Added value: +{
      +  "additionalProperties": true,
      +  "properties": {},
      +  "type": "object"
      +}
    • addedOutput schema / properties / preservation
      Added value: +{
      +  "additionalProperties": true,
      +  "properties": {},
      +  "type": "object"
      +}
  9. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses fidelity guarantees ('Zero and negative strings are not discarded'), structural preservation (rowspan/colspan, reported unit labels, row/column order), fetch limits ('Separate HWP/PDF files are not fetched or rehosted'), and truncation behavior. It also states a negative capability ('does not claim an XBRL presentation/calculation hierarchy'), which is exactly the kind of scope boundary annotations cannot express.

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?

It is front-loaded with purpose and workflow before the Args block, and the Returns paragraph is tight. The Args list partially restates schema descriptions, which is mild redundancy for a 15-parameter tool, but it keeps the call sequence readable rather than adding filler.

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 complex 15-parameter tool with attachments, comparison modes, and pagination, the description covers the full call flow, defaults, entry selection, comparison prerequisites, and content fidelity. An output schema exists, so the brief Returns paragraph is supplementary rather than load-bearing.

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?

With 100% schema description coverage, the baseline would be 3, but the description adds cross-parameter semantics the schema does not: that compare_index selects the second filing while table_index/section_index selects the first, that only selected content is compared rather than entire filings, and that overview_offset/overview_limit paginate both section and table summaries with the same slice.

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

Purpose5/5

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

The description opens with a specific verb and resource ('Explore one DART filing by receipt number') and immediately scopes the behavior ('preserving section and table structure — the main body by default, or one of its attachments'). It distinguishes itself from the sibling get_dart_financials by explicitly disclaiming XBRL hierarchy and routing normalized figures there.

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

Usage Guidelines5/5

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

It gives an explicit workflow ('Use get_dart_filings first to obtain rcept_no. Start with action=overview, then select a section or table instead of requesting a long flattened filing') and an explicit exclusion ('Use get_dart_financials for normalized figures'). It also explains when to pass entry and how comparison actions must be sequenced ('Use both overviews first').

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.