query_company_filings
Return extracted sections (not the raw 500–900 KB markdown) from a US public company’s most recent 10-K filing, so the response stays well under any client context cap. The full markdown is still materialised as a dataset for follow-up slicing.
When to use it
Section titled “When to use it”- “What did
<company>say about cybersecurity governance in their 10-K?” - “Show me their AI / cloud strategy section.”
- After
bdr_account_research, to pull a section it didn’t surface by default.
Inputs
Section titled “Inputs”| Parameter | Type | Required | Description |
|---|---|---|---|
website | string | Yes | Bare company domain (e.g. "capitalone.com"). |
sections | string[] | No | One or more of cybersecurity, ai, cloud, ma, tech, financial, risk_factors. Omit to extract all. |
keywords | string[] | No | Ad-hoc keywords for extra ~500-char extractions around each hit. |
max_chars | integer | No | Per-section cap. Default 4000, max 8000. |
limit | integer | No | Filings to consider. Default 1 (most recent). |
Returns
Section titled “Returns”JSON with the extracted sections and a dataset
handle for the full markdown.
found: false is returned when the company is not an SEC filer (common
for non-US companies) — no error, the caller continues without 10-K
data.