Previous value: -"Find a specific fact instead of paging blind. Pass a short 2-4 word phrase likely to appear VERBATIM in the prose (\"processed approximately\", \"tests processed\", \"going concern\") rather than restating the question. Case-insensitive substring match over the WHOLE document text (or the whole `section` slice), run BEFORE max_chars/offset windowing; returns matching passages (context + their own offset) instead of the paged `text`, ranking passages with a nearby figure first. If a multi-word phrase has no verbatim match, it falls back to the phrase's individual words and returns the passages holding the most of them (search.match_mode \"words\") — read those passages for the fact rather than treating them as confirmed. Use a returned offset with a follow-up call (no `search`) to read more surrounding text. Accepted aliases: `contains`, `find`, `phrase`."New value: +"Find a specific fact instead of paging blind. Pass a short 2-4 word phrase likely to appear VERBATIM in the prose (\"processed approximately\", \"tests processed\", \"going concern\") rather than restating the question. Case-insensitive substring match over the WHOLE document text (or the whole `section` slice), run BEFORE max_chars/offset windowing; returns matching passages (context + their own offset) instead of the paged `text`, ranking passages with a nearby figure first. If a multi-word phrase has no verbatim match, it falls back to the phrase's individual words and returns the passages holding the most of them (search.match_mode \"words\") — read those passages for the fact rather than treating them as confirmed. Use a returned offset with a follow-up call (no `search`) to read more surrounding text. **For TWO OR MORE facts from this same filing in one call, separate phrases with `|`** (e.g. \"Signatera revenue|tests processed\") — each is searched independently and reported under `searches[]`, keyed by `phrase`, instead of the singular `search`. This is the way to answer a compound question (\"what was revenue AND test volume in the latest 10-Q\") without a second call. Note: a phrase naming a financial TOTAL (revenue, net income, EPS, assets, cash, gross/operating profit, long-term debt, stockholders equity, shares outstanding) often has NO verbatim match at all, because filers frequently state only the growth delta/percentage in prose and report the actual total exclusively in XBRL — when a phrase names one of these, the response also attaches that concept's value for THIS SAME accession under `xbrl` (sourced like edgar_company_concept, not text-matched), so you don't need a separate edgar_company_concept call just to get the number the text search alone would report as a false \"not found\". Accepted aliases: `contains`, `find`, `phrase`."

Previous value: -"When accession is omitted, the form type of the latest filing to fetch — \"10-K\", \"10-Q\", \"8-K\", \"DEF 14A\", etc. A question asking for the \"most recent 10-K OR 10-Q\" (or otherwise not committed to one type) should OMIT this field entirely rather than guess \"10-K\" by habit — omitting form_type (along with accession) returns the single most recent filing of ANY type, and a 10-Q is very often more recent than the last 10-K since it files quarterly while the 10-K only files once a year (verified live 2026-09-25, fleet #2450: NTRA's most recent 10-Q was filed 2026-08-07, five months after its 2026-02-27 10-K — passing form_type:\"10-K\" here silently skips the newer filing and the KPI it asked about)."New value: +"When accession is omitted, the form type of the latest filing to fetch — \"10-K\", \"10-Q\", \"8-K\", \"DEF 14A\", etc. For \"the most recent 10-K OR 10-Q\" (or any \"whichever of these is newer\" question), pass a `|`-separated SET, e.g. \"10-K|10-Q\" — do NOT guess a single type (\"10-K\" by habit skips a newer 10-Q) and do NOT omit this field to get \"any type\", since a company files far more 8-Ks/Form 4s/Form 144s between annual or quarterly reports than it files the reports themselves and an empty form_type returns the single most recent filing of ANY kind (verified live 2026-09-25, fleet #2450: NTRA's single most recent SEC filing was a Form 144 insider-sale notice, filed weeks after its real 10-Q and completely unrelated to the question asked)."

Previous value: -"Find a specific fact instead of paging blind. This is a SUBSTRING match, not a relevance search — pass the exact 2-4 word phrase most likely to appear VERBATIM in the prose (\"tests processed\", \"processed approximately\", \"going concern\"), never a compound of every concept in the question. A phrase that ANDs several unrelated question-words together (\"oncology Signatera revenue test volume\") returns ZERO matches even in the CORRECT filing, because the filing's own sentence never contains all of those words together — verified live 2026-09-25 (fleet #2450) on a real Natera 10-Q that DOES report the exact number asked for: \"Signatera revenue\" and the 4-word compound above both found nothing, while the filing's own wording (\"processed approximately\", \"tests processed\") is what actually appears. When unsure of the filing's exact phrasing, prefer the SHORTEST distinctive 2-3 word fragment of the metric name itself (a unit, a verb+noun like \"processed approximately\") over restating the question. Case-insensitive substring match over the WHOLE document text (or the whole `section` slice, if both are given), run BEFORE max_chars/offset windowing. Returns every matching passage (surrounding context + its own offset in the document) instead of the normal paged `text` — use the returned offsets with a follow-up call (no `search`, `offset` set to one of them) if you need more surrounding text than the passage gives. Zero matches means try again with a SHORTER, more literal phrase before concluding the filing does not disclose it — this is a real answer about wording, not a tool failure. Accepted aliases: `contains`, `find`, `phrase`."New value: +"Find a specific fact instead of paging blind. Pass a short 2-4 word phrase likely to appear VERBATIM in the prose (\"processed approximately\", \"tests processed\", \"going concern\") rather than restating the question. Case-insensitive substring match over the WHOLE document text (or the whole `section` slice), run BEFORE max_chars/offset windowing; returns matching passages (context + their own offset) instead of the paged `text`, ranking passages with a nearby figure first. If a multi-word phrase has no verbatim match, it falls back to the phrase's individual words and returns the passages holding the most of them (search.match_mode \"words\") — read those passages for the fact rather than treating them as confirmed. Use a returned offset with a follow-up call (no `search`) to read more surrounding text. Accepted aliases: `contains`, `find`, `phrase`."

Previous value: -[
-  {
-    "form_type": "10-Q",
-    "section": "liquidity",
-    "ticker": "ACTU"
-  },
-  {
-    "accession": "0001683168-26-003909",
-    "cik": "1652935",
-    "max_chars": 30000,
-    "section": "going_concern"
-  }
-]New value: +[
+  {
+    "form_type": "10-Q",
+    "section": "liquidity",
+    "ticker": "ACTU"
+  },
+  {
+    "accession": "0001683168-26-003909",
+    "cik": "1652935",
+    "max_chars": 30000,
+    "section": "going_concern"
+  },
+  {
+    "accession": "0001628280-26-054525",
+    "search": "processed approximately",
+    "ticker": "NTRA"
+  }
+]

Added value: +{
+  "description": "Alias for `search`.",
+  "type": "string"
+}

Added value: +{
+  "description": "Alias for `search`.",
+  "type": "string"
+}

Previous value: -"When accession is omitted, the form type of the latest filing to fetch — \"10-K\", \"10-Q\", \"8-K\", \"DEF 14A\", etc."New value: +"When accession is omitted, the form type of the latest filing to fetch — \"10-K\", \"10-Q\", \"8-K\", \"DEF 14A\", etc. A question asking for the \"most recent 10-K OR 10-Q\" (or otherwise not committed to one type) should OMIT this field entirely rather than guess \"10-K\" by habit — omitting form_type (along with accession) returns the single most recent filing of ANY type, and a 10-Q is very often more recent than the last 10-K since it files quarterly while the 10-K only files once a year (verified live 2026-09-25, fleet #2450: NTRA's most recent 10-Q was filed 2026-08-07, five months after its 2026-02-27 10-K — passing form_type:\"10-K\" here silently skips the newer filing and the KPI it asked about)."

Added value: +{
+  "description": "Alias for `search`.",
+  "type": "string"
+}

Added value: +{
+  "description": "Find a specific fact instead of paging blind. This is a SUBSTRING match, not a relevance search — pass the exact 2-4 word phrase most likely to appear VERBATIM in the prose (\"tests processed\", \"processed approximately\", \"going concern\"), never a compound of every concept in the question. A phrase that ANDs several unrelated question-words together (\"oncology Signatera revenue test volume\") returns ZERO matches even in the CORRECT filing, because the filing's own sentence never contains all of those words together — verified live 2026-09-25 (fleet #2450) on a real Natera 10-Q that DOES report the exact number asked for: \"Signatera revenue\" and the 4-word compound above both found nothing, while the filing's own wording (\"processed approximately\", \"tests processed\") is what actually appears. When unsure of the filing's exact phrasing, prefer the SHORTEST distinctive 2-3 word fragment of the metric name itself (a unit, a verb+noun like \"processed approximately\") over restating the question. Case-insensitive substring match over the WHOLE document text (or the whole `section` slice, if both are given), run BEFORE max_chars/offset windowing. Returns every matching passage (surrounding context + its own offset in the document) instead of the normal paged `text` — use the returned offsets with a follow-up call (no `search`, `offset` set to one of them) if you need more surrounding text than the passage gives. Zero matches means try again with a SHORTER, more literal phrase before concluding the filing does not disclose it — this is a real answer about wording, not a tool failure. Accepted aliases: `contains`, `find`, `phrase`.",
+  "type": "string"
+}

Added value: +{
+  "description": "Alias for `ticker` / `cik` — the single-argument spelling edgar_company_filings and edgar_insider_transactions use. Takes either a ticker or a CIK.",
+  "type": "string"
+}

Previous value: -"Filer ticker (e.g. \"ACTU\"). Provide this OR cik."New value: +"Filer ticker (e.g. \"ACTU\"). Provide this OR cik. ONLY pass a ticker you are CERTAIN of — a wrong remembered ticker silently retrieves a DIFFERENT company's filing as a clean success (a \"SpaceX\" question filled with SPCE returns Virgin Galactic's S-1). For a recent IPO or any uncertain ticker, resolve first: edgar_company_filings accepts the company NAME and returns the cik — pass that cik here."

Added value: +[
+  {
+    "form_type": "10-Q",
+    "section": "liquidity",
+    "ticker": "ACTU"
+  },
+  {
+    "accession": "0001683168-26-003909",
+    "cik": "1652935",
+    "max_chars": 30000,
+    "section": "going_concern"
+  }
+]