section_language
Counted language statistics for one filing section: hedging, adverse wording, promotion, voice.
What it does
Measures HOW a section is written rather than what it says. Returns size, sentence length, long-word share, first-person and passive-voice rates, and dictionary counts in six groups -- hedging, adverse wording, uncertainty, promotional wording, forward-looking language and litigation -- each with the individual terms that hit and a rate per 1,000 words. Use it when the question is about TONE: it turns "does this read defensively?" into numbers a person can check, instead of an impression formed by reading. The lexicon and the method come back with the counts on purpose -- report the terms alongside any claim about tone. Tables and page furniture are removed before counting, because a table cell is not language; both sizes are reported. No readability index is computed and the reasons are in method.
section_language is on the free tier. A free account gets 12 agent calls per 16 hours and this is one of them; Pro is uncounted. The website's own screening allowance is counted separately.
Arguments, returns and a worked call
Everything below is generated from the same registry entry the MCP server and /openapi.json are generated from, so this page cannot name an argument that does not exist. The two examples are the same call, once over each transport.
section_language
FreeMeasures HOW a section is written rather than what it says. Returns size, sentence length, long-word share, first-person and passive-voice rates, and dictionary counts in six groups -- hedging, adverse wording, uncertainty, promotional wording, forward-looking language and litigation -- each with the individual terms that hit and a rate per 1,000 words. Use it when the question is about TONE: it turns "does this read defensively?" into numbers a person can check, instead of an impression formed by reading. The lexicon and the method come back with the counts on purpose -- report the terms alongside any claim about tone. Tables and page furniture are removed before counting, because a table cell is not language; both sizes are reported. No readability index is computed and the reasons are in `method`.
Arguments
symbol string, required — The ticker as Crush The Market spells it.
section_id string, required — A section id or alias (`mdna`, `risk-factors`), a `note-` id, or a `doc-N` id from list_filing_documents.
accession string, optional — A specific filing. Defaults to the latest annual report.
Returns
symbol, filing, section, language, note, error, as_of, source, disclaimer
> curl -s https://crushthemarket.com/api/v1/section_language \ -H "Authorization: Bearer $CTM_KEY" \ -H 'Content-Type: application/json' \ -d '{"symbol":"META","section_id":"mdna","accession":"0001628280-26-050705"}'{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "section_language", "arguments": { "symbol": "META", "section_id": "mdna", "accession": "0001628280-26-050705" } }}Can answer
bad_request — `symbol` or `section_id` is missing, or `section_id` belongs to no lane.
report_not_found — No note or document with that id in this filing.
section_not_found — The narrative lane has no section with that id.
edgar_unavailable — EDGAR did not answer after retries.
Calling section_language
- 1.Register free — an email address, no card — then create a key under API Keys on your account page. Your email address has to be verified first, and the key is shown once.
- 2.Using a chat client that speaks MCP? The MCP guide is one paste. Anything else takes bearer auth, the error codes and the limits from the REST guide.
- 3.Make the call above with your own key in it.
Every successful response carries as_of, source, a quota block saying how much of the allowance is left, and the same disclaimer this page ends on.
More for agents
Data, not advice. Do your own diligence.