Skip to main content
Glama

Resolve Entity

resolve_entity
Read-onlyIdempotent

"What's the ticker for..." / "find the CIK for..." / "what's the LEI for..." / "what's the RxCUI for..." / "look up the ID for..." / "what is X's official identifier" / "who owns X" / "is X a subsidiary of Y", resolve a user-spoken NAME to the canonical/official identifiers other tools require as input. Use FIRST whenever you have a name but need an ID. SUPPORTED TYPES: "company" (cross-source identity spine: 10-digit CIK + ticker + company_name from SEC EDGAR, legal-entity LEI from GLEIF with parent/ultimate-parent/children ownership when the LEI resolves, and security FIGI from OpenFIGI, by exact ticker map when a ticker is implied, and otherwise by name search, so NON-EQUITY instruments that never have a ticker (municipal and corporate bonds, notes, authority debt) DO resolve here; when a name matches more than one instrument it asserts nothing and returns figi_candidates to pick from, which is the correct answer to an issuer name that does not identify a single bond; every identifier is labelled with the source that established it, and an identifier that could NOT be resolved is stated explicitly under unresolved rather than omitted, accepts ticker, CIK, ISIN, LEI, or company name as input; an ISIN like "CH0038863350" resolves to the LEGAL ENTITY that issued the security via the GLEIF ISIN-to-LEI mapping, covering non-US issuers EDGAR cannot reach), "drug" (returns RxCUI + ingredient + brand from RxNorm + pipeworx://rxnorm/concept/{rxcui} citation; accepts brand or generic name). LEI/FIGI enrichment degrades gracefully, if GLEIF or OpenFIGI is unavailable, the EDGAR identifiers still return. Each call cascades through several lookup endpoints internally, using resolve_entity replaces 2-3 manual lookups.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "company",
      "value": "AAPL"
    },
    "name": "resolve_entity"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYesEntity type: "company", "drug" or "lei" (a 20-character LEI; "company" also recognises an LEI by its check digits).
valueYesFor company: ticker (AAPL), CIK (0000320193 or 320193), LEI (HWUPKR0MPOU8FGXBT394), or name. A bare number is read as an SEC CIK only as 320193 or 0000320193; with a non-US `country`, or with 8-9 digits starting with 0 (a Companies House number), it is not a CIK and is not asserted as one. A bare number of 7 digits or fewer sent without `country` is always read as an SEC CIK, so a short register number (for example an Irish CRO or a US state filing number) that equals a real CIK will resolve to that SEC filer; send a non-US `country` with a foreign register number. A US state filing number cannot be resolved by number; search by company name instead. For drug: brand or generic name (e.g., "ozempic", "metformin"). Pass the ENTITY NAME ONLY, for a bond that is the ISSUER exactly as printed ("NEW YORK ST DORM AUTH"), never the question's full noun phrase ("NEW YORK ST DORM AUTH revenue bonds"): the FIGI lookup matches instrument names, so trailing security-class words match nothing.
countryNoOPTIONAL ISO 3166-1 alpha-2 of the country whose business register you mean ("NO", "FI", "JP", "GB", "FR", "EE", "BR"). Narrows the national-register fan-out and is often the difference between the right company and a US namesake, "Apple" with country "NO" is a Norwegian company, not Apple Inc. Omitting it searches every register we can name, which is the right default when you do not know. A bare number with a non-US country is that country's register number, never read as an SEC CIK (a 10-digit number still is). company only; ignored for drug.

Output Schema

NameRequiredDescriptionDefault
idsYesEvery identifier established: cik, ticker, company_name, lei, figi, isin, cusip, register_id, register_country. A key absent here appears in `unresolved` with a reason, never silently dropped.
typeYes
brandNo
notesNo
queryYes
relatedNoEntities that collapsed INTO the match, each carrying `collapsed_by`.
sourcesYesPer-identifier provenance. Every key in `ids` has a matching key here.
resolvedYesAt least one identifier was established. Read `match_basis` for WHAT the ids rest on and `unresolved` for what is missing; a company can be resolved in a national register with no CIK at all. When `match_status` is "matched" this is true. `resolved: true` with `match_status: "ambiguous"` is the one residual combination and it means exactly this: SEC named ONE filer on an exact hit that is also a name or word (`match_basis` "sec_ticker_word" or "sec_name", e.g. "Bolt", "Zoom"), and the registers hold rivals with the same name, listed under `alternates`. An exact ticker symbol ("AAPL") is never in that state, and a ticker that is also the name of a DIFFERENT registrant ("HP") is `resolved: false` with `match_basis` "sec_ticker_rival_name".
searchedNoEVERY register asked, with its own as-of date and row count. A register that could not be reached carries `error`, 0 rows with an error is "we could not ask", 0 rows without one is "nothing is there", and they are different answers.
registersNoThe matched entity as every register that carries it, the match (flagged `matched: true`) plus anything that collapsed into it. A Companies House number AND the LEI that crosswalks to it are the SAME answer, not rivals.
resourcesNo
successorNoPresent only when SEC's own records show this CIK is the PREDECESSOR of a successor registrant (the counterpart of `predecessor`). `cik` / `company_name` name the registrant that now holds the listed security and the filings after `succession_date`.
alternatesNoEntities that share the typed string with the entity in `ids`, in ONE fixed order for the same input (SEC registrants first when the basis is "sec_ticker_rival_name", then register rows by score, register_key, register_id), slimmed to who and where (the full rows are in `candidates`). For an exact ticker they are lookalikes of the symbol and do not make the answer ambiguous; for "sec_ticker_word" and "sec_name" they are the rivals the registers hold.
candidatesNoRivals, best first. Populated on "ambiguous" and on "matched" alike. Register rows come from the register search; SEC registrants whose name matches (register_key "US-SEC-EDGAR", register_id the CIK, `cik` set) are added at the END, from the SEC leg: they were NOT part of the match scoring, their `score` is computed apart, and they never change `match_status` or what is asserted (fleet #4574).
ingredientNo
lei_recordNoPresent when the input was an LEI GLEIF holds: GLEIF's own record, verbatim. `active` is true only when `entity_status` is "ACTIVE" and `registration_status` is "ISSUED"; a LAPSED or RETIRED LEI has `active: false` and the sentence in `notes` says so. A lapsed LEI is unmaintained reference data, not evidence the company stopped trading.
unresolvedYesPer-identifier reason an id could NOT be established, the honest twin of `ids`.
match_basisNoWhat `ids.cik` rests on, present whenever a CIK is asserted or withheld on this basis. "sec_ticker": the typed string is exactly the ticker symbol of one listed security, and it is not also the issuer's own first word; this settles the answer whatever the registers hold. "sec_ticker_word": also a ticker, but the typed word is the start of the issuer's name (Bolt, Uber), so register entities with that name are real rivals. "sec_name": a name match in SEC's company list. "sec_name_normalized": the typed name EQUALS the registrant's name in SEC's company list once a leading "The", punctuation and the Inc./Corp./Co./Ltd. spelling are set aside ("The Coca-Cola Company" equals COCA COLA CO), and exactly one SEC registrant has that name; nothing merely similar is guessed, and two registrants with the same normalised name assert neither (they are listed under `sec_alternatives`). "sec_cik": the caller supplied the CIK. "sec_ticker_rival_name": the string is the ticker of one SEC registrant AND the name of a different one (HP is Helmerich & Payne's ticker and the name of HP INC, ticker HPQ); neither is asserted, `resolved` is false, `match_status` is "ambiguous", and both head `alternates`. "lei_sec_name_state": SEC's own record for the CIK carries the same legal name and the same US state of incorporation as the LEI: the input was that LEI (see `sec_registrant`), or a company name that found no CIK in SEC's lists but whose exact GLEIF legal-name LEI could be confirmed this way. "sec_ticker_unchecked": the string is a ticker symbol, but SEC's registrant-name index did not answer, so whether it is also another registrant's name could not be checked; nothing is asserted, `resolved` is false, `match_status` is "ambiguous", the ticker holder is under `cik_withheld`, and a retry completes it.
predecessorNoPresent only when SEC's own records show this CIK is the SUCCESSOR registrant of another (a holding-company reorganisation moved the listed security to a new registrant). `cik` / `company_name` name the registrant that holds the earlier filings and XBRL history; `last_period_end` is the period end of the last periodic report the predecessor filed on its own (not counting a report filed jointly under both CIKs, whose facts sit under the successor), i.e. where the predecessor's own facts series ends. Never inferred from a name, and the two registrants' data are never merged.
cik_withheldNoA CIK that came back from a FUZZY SEC name match and is NOT asserted, because the spine matched a stronger non-US candidate, or `match_status` is "ambiguous" or "incomplete" and the SEC hit was not an exact ticker, CIK or legal name (fleet #3606). The number is here so a caller who wanted the US filer can still use it; what changed is that we no longer claim it IS the answer. Also carries the CIK reading of a bare number that is not a CIK in either form EDGAR uses (fleet #4522): `resolved` is false, `company_name_withheld` is SEC's name for that CIK, and `unresolved.cik` says why. See `unresolved.cik` for the reason.
lei_withheldNoA LEI that is NOT asserted: it matched the bare string exactly in GLEIF, but `match_status` is "ambiguous" or "incomplete" so the registers cannot say which company that string means, and a GLEIF hit on the same string is the same guess from another register. `relationships` is withheld with it. A LEI from an exact SEC hit, or from a complete legal name carrying its legal form, is never withheld. See `unresolved.lei`.
match_statusNoThe headline to branch on. "matched" is ONE entity: a national-register match, or, when `match_basis` is "sec_ticker", a typed string that is exactly the ticker symbol of one listed security (the register search's own verdict is then kept in `register_match_status` and its lookalikes in `alternates`). "ambiguous" is an ANSWER, not a failure: two companies matched the name equally well and both are in `candidates`. "no_match" means every register in `searched` was asked and none carried it. "incomplete" means one of them could NOT be asked (it carries an `error` in `searched[]`), so the candidate set is short by an unknown amount and no id is asserted, distinct from "ambiguous" because a RETRY is what resolves it, not a narrower query; `fanout_incomplete` names the unreachable registers and carries, under `withheld_match`, the candidate that would have been returned on a complete fan-out.
figi_withheldNoA FIGI that is NOT asserted. Either it matched this name in OpenFIGI (`figi_match: "name_search"`) while `match_status` is "incomplete", a name search cannot tell a company apart from a security carrying its name, and the registers that would have settled it are the ones we could not ask, or it is a `ticker_map` FIGI whose ticker came from a FUZZY SEC name match that is itself withheld (`cik_withheld`), so the mapping inherits the doubt. A `ticker_map` FIGI from an EXACT SEC hit (a real ticker, a CIK, an exact legal name) is never withheld. Carried so a caller who accepts the caveat can use it; see `unresolved.figi`.
match_scoringNoThe margin rule's own inputs, so a caller can see WHY it fell where it did.
sec_registrantNoPresent when the input was an LEI: whether the legal entity is an SEC registrant. "found": `ids.cik` is asserted, the CIK whose SEC record carries the same legal name and the same US state of incorporation as the LEI (`match_basis` "lei_sec_name_state"). "none_found": SEC's registrant lookup and its company-name lookup both answered and matched no registrant with that legal name (a leading "The", punctuation and Inc./Corp./Co./Ltd. spelling are set aside), so `ids.cik` is absent and `unresolved.cik` says what was matched; it is not a statement that the entity is not an SEC registrant. Most LEIs are this. "not_established": it could not be settled, SEC did not answer, or a name match could not be confirmed against a state (every non-US jurisdiction), so no CIK is asserted; the unconfirmed CIK, if any, is under `cik_withheld`.
ticker_withheldNoThe ticker of a FUZZY SEC name match that is NOT asserted, withheld together with `cik_withheld` because it is the same guess. Carried so a caller who meant the US filer can still use it; see `unresolved.ticker`.
sec_alternativesNoEDGAR's other name-matching candidates: distinct companies, deduped by CIK, excluding this issuer's own share classes, surfaced instead of dropped so a caller can tell a genuinely CONTESTED name match from a clean one. When two or more SEC registrants have the SAME name once a leading "The", punctuation and Inc./Corp./Co./Ltd. spelling are set aside, no CIK is asserted and all of them are listed here (fleet #4550).
fanout_incompleteNoPresent IFF at least one register in `searched[]` carried an `error`, set even when `match_status` stayed "ambiguous". `withheld_match` is the candidate this call declined to ASSERT because a register was missing, carried rather than discarded so a caller who accepts the caveat can still use it.
match_explanationNoPlain words. Always present when the spine ran, and required on "ambiguous" and "no_match".
company_name_withheldNoThe company name of a FUZZY SEC name match that is NOT asserted, withheld together with `cik_withheld`. See `unresolved.cik`.
register_match_statusNoPresent only when `match_status` was settled by an exact ticker rather than by the registers: the register search's own verdict, verbatim. It never changes which security the ticker names.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedOutput schema / properties / candidates / description
      Previous value: -"Rivals, best first. Populated on \"ambiguous\" and on \"matched\" alike."New value: +"Rivals, best first. Populated on \"ambiguous\" and on \"matched\" alike. Register rows come from the register search; SEC registrants whose name matches (register_key \"US-SEC-EDGAR\", register_id the CIK, `cik` set) are added at the END, from the SEC leg: they were NOT part of the match scoring, their `score` is computed apart, and they never change `match_status` or what is asserted (fleet #4574)."
    • addedOutput schema / properties / candidates / items / properties / cik
      Added value: +{
      +  "description": "SEC rows only (register_key \"US-SEC-EDGAR\"): the registrant's 10-digit CIK, the same value as `register_id`. Fleet #4574.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / candidates / items / properties / sec_name_match
      Added value: +{
      +  "description": "SEC rows only: how the SEC leg reached this registrant. \"asserted\": it is `ids.cik`. \"withheld\": it is `cik_withheld`, a name match not asserted. \"sec_listed\": SEC's own name list names it for the typed string (`sec_alternatives`).",
      +  "enum": [
      +    "asserted",
      +    "withheld",
      +    "sec_listed"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / candidates / items / properties / ticker
      Added value: +{
      +  "description": "SEC rows only: the ticker SEC lists for that CIK today, when it lists one. A superseded registrant carries none.",
      +  "type": "string"
      +}
  2. Changed2 schema fields changed
    • addedOutput schema / properties / predecessor
      Added value: +{
      +  "description": "Present only when SEC's own records show this CIK is the SUCCESSOR registrant of another (a holding-company reorganisation moved the listed security to a new registrant). `cik` / `company_name` name the registrant that holds the earlier filings and XBRL history; `last_period_end` is the period end of the last periodic report the predecessor filed on its own (not counting a report filed jointly under both CIKs, whose facts sit under the successor), i.e. where the predecessor's own facts series ends. Never inferred from a name, and the two registrants' data are never merged.",
      +  "properties": {
      +    "basis": {
      +      "description": "\"sec_8k12b_joint_filing\": the successor filed an 8-K12B (SEC's succession notice) and, within days, a registration-statement amendment jointly with this registrant. \"sec_8k12b_cover_file_number\": the 8-K12B cover prints this registrant's Commission file number, which SEC holds under this CIK.",
      +      "enum": [
      +        "sec_8k12b_joint_filing",
      +        "sec_8k12b_cover_file_number"
      +      ],
      +      "type": "string"
      +    },
      +    "cik": {
      +      "type": "string"
      +    },
      +    "company_name": {
      +      "type": "string"
      +    },
      +    "evidence": {
      +      "description": "The two SEC records the link rests on: the successor's 8-K12B (SEC's formal succession notice) and a registration-statement amendment filed jointly by both registrants, with the registration numbers each filed under.",
      +      "properties": {
      +        "joint_filing": {
      +          "properties": {
      +            "accession": {
      +              "type": "string"
      +            },
      +            "filing_date": {
      +              "type": "string"
      +            },
      +            "form": {
      +              "type": "string"
      +            },
      +            "predecessor_file_number": {
      +              "type": "string"
      +            },
      +            "successor_file_number": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        },
      +        "succession_notice": {
      +          "properties": {
      +            "accession": {
      +              "type": "string"
      +            },
      +            "filed_by_cik": {
      +              "type": "string"
      +            },
      +            "filing_date": {
      +              "type": "string"
      +            },
      +            "form": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "last_period_end": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "note": {
      +      "type": "string"
      +    },
      +    "succession_date": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedOutput schema / properties / successor
      Added value: +{
      +  "description": "Present only when SEC's own records show this CIK is the PREDECESSOR of a successor registrant (the counterpart of `predecessor`). `cik` / `company_name` name the registrant that now holds the listed security and the filings after `succession_date`.",
      +  "properties": {
      +    "basis": {
      +      "enum": [
      +        "sec_8k12b_joint_filing",
      +        "sec_8k12b_cover_file_number"
      +      ],
      +      "type": "string"
      +    },
      +    "cik": {
      +      "type": "string"
      +    },
      +    "company_name": {
      +      "type": "string"
      +    },
      +    "evidence": {
      +      "description": "The two SEC records the link rests on: the successor's 8-K12B (SEC's formal succession notice) and a registration-statement amendment filed jointly by both registrants, with the registration numbers each filed under.",
      +      "properties": {
      +        "joint_filing": {
      +          "properties": {
      +            "accession": {
      +              "type": "string"
      +            },
      +            "filing_date": {
      +              "type": "string"
      +            },
      +            "form": {
      +              "type": "string"
      +            },
      +            "predecessor_file_number": {
      +              "type": "string"
      +            },
      +            "successor_file_number": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        },
      +        "succession_notice": {
      +          "properties": {
      +            "accession": {
      +              "type": "string"
      +            },
      +            "filed_by_cik": {
      +              "type": "string"
      +            },
      +            "filing_date": {
      +              "type": "string"
      +            },
      +            "form": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "note": {
      +      "type": "string"
      +    },
      +    "succession_date": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  3. Changed10 schema fields changed
    • changedInput schema / properties / country / description
      Previous value: -"OPTIONAL ISO 3166-1 alpha-2 of the country whose business register you mean (\"NO\", \"FI\", \"JP\", \"GB\", \"FR\", \"EE\", \"BR\"). Narrows the national-register fan-out and is often the difference between the right company and a US namesake, \"Apple\" with country \"NO\" is a Norwegian company, not Apple Inc. Omitting it searches every register we can name, which is the right default when you do not know. company only; ignored for drug."New value: +"OPTIONAL ISO 3166-1 alpha-2 of the country whose business register you mean (\"NO\", \"FI\", \"JP\", \"GB\", \"FR\", \"EE\", \"BR\"). Narrows the national-register fan-out and is often the difference between the right company and a US namesake, \"Apple\" with country \"NO\" is a Norwegian company, not Apple Inc. Omitting it searches every register we can name, which is the right default when you do not know. A bare number with a non-US country is that country's register number, never read as an SEC CIK (a 10-digit number still is). company only; ignored for drug."
    • changedInput schema / properties / value / description
      Previous value: -"For company: ticker (AAPL), CIK (0000320193), LEI (HWUPKR0MPOU8FGXBT394), or name. For drug: brand or generic name (e.g., \"ozempic\", \"metformin\"). Pass the ENTITY NAME ONLY, for a bond that is the ISSUER exactly as printed (\"NEW YORK ST DORM AUTH\"), never the question's full noun phrase (\"NEW YORK ST DORM AUTH revenue bonds\"): the FIGI lookup matches instrument names, so trailing security-class words match nothing."New value: +"For company: ticker (AAPL), CIK (0000320193 or 320193), LEI (HWUPKR0MPOU8FGXBT394), or name. A bare number is read as an SEC CIK only as 320193 or 0000320193; with a non-US `country`, or with 8-9 digits starting with 0 (a Companies House number), it is not a CIK and is not asserted as one. A bare number of 7 digits or fewer sent without `country` is always read as an SEC CIK, so a short register number (for example an Irish CRO or a US state filing number) that equals a real CIK will resolve to that SEC filer; send a non-US `country` with a foreign register number. A US state filing number cannot be resolved by number; search by company name instead. For drug: brand or generic name (e.g., \"ozempic\", \"metformin\"). Pass the ENTITY NAME ONLY, for a bond that is the ISSUER exactly as printed (\"NEW YORK ST DORM AUTH\"), never the question's full noun phrase (\"NEW YORK ST DORM AUTH revenue bonds\"): the FIGI lookup matches instrument names, so trailing security-class words match nothing."
    • changedOutput schema / properties / candidates / items / properties / id_round_trips / description
      Previous value: -"Whether `register_id`, sent back to resolve_entity as `value`, resolves to this same entity. true: the LEI (GLEIF rows), a CIK (US-SEC-EDGAR rows), and the BR, AU, PE, SG and LV register ids. false: DISPLAY-ONLY here, because a short digits-only id is read as an SEC CIK before any register is asked (a GB company number resolved to an unrelated SEC filer), and the other registers are not searched by id. `detail_tool` names where such an id does go."New value: +"Whether `register_id`, sent back to resolve_entity as `value`, resolves to this same entity. true: the LEI (GLEIF rows), a CIK (US-SEC-EDGAR rows), and the BR, AU, PE, SG and LV register ids. false: DISPLAY-ONLY here, because these registers are not searched by id: a bare number sent back is not asserted as an SEC CIK when it has leading zeros and 8-9 digits (a GB company number) or comes with a non-US `country` (fleet #4522), and otherwise answers \"no such SEC registrant\". `detail_tool` names where such an id does go."
    • changedOutput schema / properties / cik_withheld / description
      Previous value: -"A CIK that came back from a FUZZY SEC name match and is NOT asserted, because the spine matched a stronger non-US candidate, or `match_status` is \"ambiguous\" or \"incomplete\" and the SEC hit was not an exact ticker, CIK or legal name (fleet #3606). The number is here so a caller who wanted the US filer can still use it; what changed is that we no longer claim it IS the answer. See `unresolved.cik` for the reason."New value: +"A CIK that came back from a FUZZY SEC name match and is NOT asserted, because the spine matched a stronger non-US candidate, or `match_status` is \"ambiguous\" or \"incomplete\" and the SEC hit was not an exact ticker, CIK or legal name (fleet #3606). The number is here so a caller who wanted the US filer can still use it; what changed is that we no longer claim it IS the answer. Also carries the CIK reading of a bare number that is not a CIK in either form EDGAR uses (fleet #4522): `resolved` is false, `company_name_withheld` is SEC's name for that CIK, and `unresolved.cik` says why. See `unresolved.cik` for the reason."
    • changedOutput schema / properties / match_basis / description
      Previous value: -"What `ids.cik` rests on, present whenever a CIK is asserted or withheld on this basis. \"sec_ticker\": the typed string is exactly the ticker symbol of one listed security, and it is not also the issuer's own first word; this settles the answer whatever the registers hold. \"sec_ticker_word\": also a ticker, but the typed word is the start of the issuer's name (Bolt, Uber), so register entities with that name are real rivals. \"sec_name\": a name match in SEC's company list. \"sec_cik\": the caller supplied the CIK. \"sec_ticker_rival_name\": the string is the ticker of one SEC registrant AND the name of a different one (HP is Helmerich & Payne's ticker and the name of HP INC, ticker HPQ); neither is asserted, `resolved` is false, `match_status` is \"ambiguous\", and both head `alternates`. \"lei_sec_name_state\": the input was an LEI and SEC's own record for the CIK carries the same legal name and the same US state of incorporation as the LEI (see `sec_registrant`). \"sec_ticker_unchecked\": the string is a ticker symbol, but SEC's registrant-name index did not answer, so whether it is also another registrant's name could not be checked; nothing is asserted, `resolved` is false, `match_status` is \"ambiguous\", the ticker holder is under `cik_withheld`, and a retry completes it."New value: +"What `ids.cik` rests on, present whenever a CIK is asserted or withheld on this basis. \"sec_ticker\": the typed string is exactly the ticker symbol of one listed security, and it is not also the issuer's own first word; this settles the answer whatever the registers hold. \"sec_ticker_word\": also a ticker, but the typed word is the start of the issuer's name (Bolt, Uber), so register entities with that name are real rivals. \"sec_name\": a name match in SEC's company list. \"sec_name_normalized\": the typed name EQUALS the registrant's name in SEC's company list once a leading \"The\", punctuation and the Inc./Corp./Co./Ltd. spelling are set aside (\"The Coca-Cola Company\" equals COCA COLA CO), and exactly one SEC registrant has that name; nothing merely similar is guessed, and two registrants with the same normalised name assert neither (they are listed under `sec_alternatives`). \"sec_cik\": the caller supplied the CIK. \"sec_ticker_rival_name\": the string is the ticker of one SEC registrant AND the name of a different one (HP is Helmerich & Payne's ticker and the name of HP INC, ticker HPQ); neither is asserted, `resolved` is false, `match_status` is \"ambiguous\", and both head `alternates`. \"lei_sec_name_state\": SEC's own record for the CIK carries the same legal name and the same US state of incorporation as the LEI: the input was that LEI (see `sec_registrant`), or a company name that found no CIK in SEC's lists but whose exact GLEIF legal-name LEI could be confirmed this way. \"sec_ticker_unchecked\": the string is a ticker symbol, but SEC's registrant-name index did not answer, so whether it is also another registrant's name could not be checked; nothing is asserted, `resolved` is false, `match_status` is \"ambiguous\", the ticker holder is under `cik_withheld`, and a retry completes it."
    • changedOutput schema / properties / match_basis / enum
      Previous value: -[
      -  "sec_ticker",
      -  "sec_ticker_word",
      -  "sec_name",
      -  "sec_cik",
      -  "sec_ticker_rival_name",
      -  "sec_ticker_unchecked",
      -  "lei_sec_name_state"
      -]New value: +[
      +  "sec_ticker",
      +  "sec_ticker_word",
      +  "sec_name",
      +  "sec_name_normalized",
      +  "sec_cik",
      +  "sec_ticker_rival_name",
      +  "sec_ticker_unchecked",
      +  "lei_sec_name_state"
      +]
    • changedOutput schema / properties / registers / items / properties / id_round_trips / description
      Previous value: -"Whether `register_id`, sent back to resolve_entity as `value`, resolves to this same entity. true: the LEI (GLEIF rows), a CIK (US-SEC-EDGAR rows), and the BR, AU, PE, SG and LV register ids. false: DISPLAY-ONLY here, because a short digits-only id is read as an SEC CIK before any register is asked (a GB company number resolved to an unrelated SEC filer), and the other registers are not searched by id. `detail_tool` names where such an id does go."New value: +"Whether `register_id`, sent back to resolve_entity as `value`, resolves to this same entity. true: the LEI (GLEIF rows), a CIK (US-SEC-EDGAR rows), and the BR, AU, PE, SG and LV register ids. false: DISPLAY-ONLY here, because these registers are not searched by id: a bare number sent back is not asserted as an SEC CIK when it has leading zeros and 8-9 digits (a GB company number) or comes with a non-US `country` (fleet #4522), and otherwise answers \"no such SEC registrant\". `detail_tool` names where such an id does go."
    • changedOutput schema / properties / related / items / properties / id_round_trips / description
      Previous value: -"Whether `register_id`, sent back to resolve_entity as `value`, resolves to this same entity. true: the LEI (GLEIF rows), a CIK (US-SEC-EDGAR rows), and the BR, AU, PE, SG and LV register ids. false: DISPLAY-ONLY here, because a short digits-only id is read as an SEC CIK before any register is asked (a GB company number resolved to an unrelated SEC filer), and the other registers are not searched by id. `detail_tool` names where such an id does go."New value: +"Whether `register_id`, sent back to resolve_entity as `value`, resolves to this same entity. true: the LEI (GLEIF rows), a CIK (US-SEC-EDGAR rows), and the BR, AU, PE, SG and LV register ids. false: DISPLAY-ONLY here, because these registers are not searched by id: a bare number sent back is not asserted as an SEC CIK when it has leading zeros and 8-9 digits (a GB company number) or comes with a non-US `country` (fleet #4522), and otherwise answers \"no such SEC registrant\". `detail_tool` names where such an id does go."
    • changedOutput schema / properties / sec_alternatives / description
      Previous value: -"EDGAR's other name-matching candidates: distinct companies, deduped by CIK, excluding this issuer's own share classes, surfaced instead of dropped so a caller can tell a genuinely CONTESTED name match from a clean one."New value: +"EDGAR's other name-matching candidates: distinct companies, deduped by CIK, excluding this issuer's own share classes, surfaced instead of dropped so a caller can tell a genuinely CONTESTED name match from a clean one. When two or more SEC registrants have the SAME name once a leading \"The\", punctuation and Inc./Corp./Co./Ltd. spelling are set aside, no CIK is asserted and all of them are listed here (fleet #4550)."
    • changedOutput schema / properties / sec_registrant / description
      Previous value: -"Present when the input was an LEI: whether the legal entity is an SEC registrant. \"found\": `ids.cik` is asserted, the CIK whose SEC record carries the same legal name and the same US state of incorporation as the LEI (`match_basis` \"lei_sec_name_state\"). \"none_found\": SEC's registrant lookup answered and holds no registrant of that name, there is NO SEC entity, `ids.cik` is absent and `unresolved.cik` says so; most LEIs are this. \"not_established\": it could not be settled, SEC did not answer, or a name match could not be confirmed against a state (every non-US jurisdiction), so no CIK is asserted; the unconfirmed CIK, if any, is under `cik_withheld`."New value: +"Present when the input was an LEI: whether the legal entity is an SEC registrant. \"found\": `ids.cik` is asserted, the CIK whose SEC record carries the same legal name and the same US state of incorporation as the LEI (`match_basis` \"lei_sec_name_state\"). \"none_found\": SEC's registrant lookup and its company-name lookup both answered and matched no registrant with that legal name (a leading \"The\", punctuation and Inc./Corp./Co./Ltd. spelling are set aside), so `ids.cik` is absent and `unresolved.cik` says what was matched; it is not a statement that the entity is not an SEC registrant. Most LEIs are this. \"not_established\": it could not be settled, SEC did not answer, or a name match could not be confirmed against a state (every non-US jurisdiction), so no CIK is asserted; the unconfirmed CIK, if any, is under `cik_withheld`."
  4. Changed10 schema fields changed
    • changedInput schema / properties / type / description
      Previous value: -"Entity type: \"company\" or \"drug\"."New value: +"Entity type: \"company\", \"drug\" or \"lei\" (a 20-character LEI; \"company\" also recognises an LEI by its check digits)."
    • changedInput schema / properties / type / enum
      Previous value: -[
      -  "company",
      -  "drug"
      -]New value: +[
      +  "company",
      +  "drug",
      +  "lei"
      +]
    • changedInput schema / properties / value / description
      Previous value: -"For company: ticker (AAPL), CIK (0000320193), or name. For drug: brand or generic name (e.g., \"ozempic\", \"metformin\"). Pass the ENTITY NAME ONLY, for a bond that is the ISSUER exactly as printed (\"NEW YORK ST DORM AUTH\"), never the question's full noun phrase (\"NEW YORK ST DORM AUTH revenue bonds\"): the FIGI lookup matches instrument names, so trailing security-class words match nothing."New value: +"For company: ticker (AAPL), CIK (0000320193), LEI (HWUPKR0MPOU8FGXBT394), or name. For drug: brand or generic name (e.g., \"ozempic\", \"metformin\"). Pass the ENTITY NAME ONLY, for a bond that is the ISSUER exactly as printed (\"NEW YORK ST DORM AUTH\"), never the question's full noun phrase (\"NEW YORK ST DORM AUTH revenue bonds\"): the FIGI lookup matches instrument names, so trailing security-class words match nothing."
    • addedOutput schema / properties / candidates / items / properties / id_round_trips
      Added value: +{
      +  "description": "Whether `register_id`, sent back to resolve_entity as `value`, resolves to this same entity. true: the LEI (GLEIF rows), a CIK (US-SEC-EDGAR rows), and the BR, AU, PE, SG and LV register ids. false: DISPLAY-ONLY here, because a short digits-only id is read as an SEC CIK before any register is asked (a GB company number resolved to an unrelated SEC filer), and the other registers are not searched by id. `detail_tool` names where such an id does go.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / lei_record
      Added value: +{
      +  "description": "Present when the input was an LEI GLEIF holds: GLEIF's own record, verbatim. `active` is true only when `entity_status` is \"ACTIVE\" and `registration_status` is \"ISSUED\"; a LAPSED or RETIRED LEI has `active: false` and the sentence in `notes` says so. A lapsed LEI is unmaintained reference data, not evidence the company stopped trading.",
      +  "properties": {
      +    "active": {
      +      "type": "boolean"
      +    },
      +    "entity_status": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "gleif_url": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "jurisdiction": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "last_update": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "legal_form": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "legal_name": {
      +      "type": "string"
      +    },
      +    "next_renewal": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "registered_as": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "registration_authority": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "registration_status": {
      +      "description": "ISSUED, LAPSED, RETIRED, ANNULLED, MERGED, DUPLICATE, PENDING_TRANSFER, ... as GLEIF states it.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
    • changedOutput schema / properties / match_basis / description
      Previous value: -"What `ids.cik` rests on, present whenever a CIK is asserted or withheld on this basis. \"sec_ticker\": the typed string is exactly the ticker symbol of one listed security, and it is not also the issuer's own first word; this settles the answer whatever the registers hold. \"sec_ticker_word\": also a ticker, but the typed word is the start of the issuer's name (Bolt, Uber), so register entities with that name are real rivals. \"sec_name\": a name match in SEC's company list. \"sec_cik\": the caller supplied the CIK. \"sec_ticker_rival_name\": the string is the ticker of one SEC registrant AND the name of a different one (HP is Helmerich & Payne's ticker and the name of HP INC, ticker HPQ); neither is asserted, `resolved` is false, `match_status` is \"ambiguous\", and both head `alternates`. \"sec_ticker_unchecked\": the string is a ticker symbol, but SEC's registrant-name index did not answer, so whether it is also another registrant's name could not be checked; nothing is asserted, `resolved` is false, `match_status` is \"ambiguous\", the ticker holder is under `cik_withheld`, and a retry completes it."New value: +"What `ids.cik` rests on, present whenever a CIK is asserted or withheld on this basis. \"sec_ticker\": the typed string is exactly the ticker symbol of one listed security, and it is not also the issuer's own first word; this settles the answer whatever the registers hold. \"sec_ticker_word\": also a ticker, but the typed word is the start of the issuer's name (Bolt, Uber), so register entities with that name are real rivals. \"sec_name\": a name match in SEC's company list. \"sec_cik\": the caller supplied the CIK. \"sec_ticker_rival_name\": the string is the ticker of one SEC registrant AND the name of a different one (HP is Helmerich & Payne's ticker and the name of HP INC, ticker HPQ); neither is asserted, `resolved` is false, `match_status` is \"ambiguous\", and both head `alternates`. \"lei_sec_name_state\": the input was an LEI and SEC's own record for the CIK carries the same legal name and the same US state of incorporation as the LEI (see `sec_registrant`). \"sec_ticker_unchecked\": the string is a ticker symbol, but SEC's registrant-name index did not answer, so whether it is also another registrant's name could not be checked; nothing is asserted, `resolved` is false, `match_status` is \"ambiguous\", the ticker holder is under `cik_withheld`, and a retry completes it."
    • changedOutput schema / properties / match_basis / enum
      Previous value: -[
      -  "sec_ticker",
      -  "sec_ticker_word",
      -  "sec_name",
      -  "sec_cik",
      -  "sec_ticker_rival_name",
      -  "sec_ticker_unchecked"
      -]New value: +[
      +  "sec_ticker",
      +  "sec_ticker_word",
      +  "sec_name",
      +  "sec_cik",
      +  "sec_ticker_rival_name",
      +  "sec_ticker_unchecked",
      +  "lei_sec_name_state"
      +]
    • addedOutput schema / properties / registers / items / properties / id_round_trips
      Added value: +{
      +  "description": "Whether `register_id`, sent back to resolve_entity as `value`, resolves to this same entity. true: the LEI (GLEIF rows), a CIK (US-SEC-EDGAR rows), and the BR, AU, PE, SG and LV register ids. false: DISPLAY-ONLY here, because a short digits-only id is read as an SEC CIK before any register is asked (a GB company number resolved to an unrelated SEC filer), and the other registers are not searched by id. `detail_tool` names where such an id does go.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / related / items / properties / id_round_trips
      Added value: +{
      +  "description": "Whether `register_id`, sent back to resolve_entity as `value`, resolves to this same entity. true: the LEI (GLEIF rows), a CIK (US-SEC-EDGAR rows), and the BR, AU, PE, SG and LV register ids. false: DISPLAY-ONLY here, because a short digits-only id is read as an SEC CIK before any register is asked (a GB company number resolved to an unrelated SEC filer), and the other registers are not searched by id. `detail_tool` names where such an id does go.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / sec_registrant
      Added value: +{
      +  "description": "Present when the input was an LEI: whether the legal entity is an SEC registrant. \"found\": `ids.cik` is asserted, the CIK whose SEC record carries the same legal name and the same US state of incorporation as the LEI (`match_basis` \"lei_sec_name_state\"). \"none_found\": SEC's registrant lookup answered and holds no registrant of that name, there is NO SEC entity, `ids.cik` is absent and `unresolved.cik` says so; most LEIs are this. \"not_established\": it could not be settled, SEC did not answer, or a name match could not be confirmed against a state (every non-US jurisdiction), so no CIK is asserted; the unconfirmed CIK, if any, is under `cik_withheld`.",
      +  "enum": [
      +    "found",
      +    "none_found",
      +    "not_established"
      +  ],
      +  "type": "string"
      +}
  5. Changed2 schema fields changed
    • changedOutput schema / properties / match_basis / description
      Previous value: -"What `ids.cik` rests on, present whenever a CIK is asserted or withheld on this basis. \"sec_ticker\": the typed string is exactly the ticker symbol of one listed security, and it is not also the issuer's own first word; this settles the answer whatever the registers hold. \"sec_ticker_word\": also a ticker, but the typed word is the start of the issuer's name (Bolt, Uber), so register entities with that name are real rivals. \"sec_name\": a name match in SEC's company list. \"sec_cik\": the caller supplied the CIK. \"sec_ticker_rival_name\": the string is the ticker of one SEC registrant AND the name of a different one (HP is Helmerich & Payne's ticker and the name of HP INC, ticker HPQ); neither is asserted, `resolved` is false, `match_status` is \"ambiguous\", and both head `alternates`."New value: +"What `ids.cik` rests on, present whenever a CIK is asserted or withheld on this basis. \"sec_ticker\": the typed string is exactly the ticker symbol of one listed security, and it is not also the issuer's own first word; this settles the answer whatever the registers hold. \"sec_ticker_word\": also a ticker, but the typed word is the start of the issuer's name (Bolt, Uber), so register entities with that name are real rivals. \"sec_name\": a name match in SEC's company list. \"sec_cik\": the caller supplied the CIK. \"sec_ticker_rival_name\": the string is the ticker of one SEC registrant AND the name of a different one (HP is Helmerich & Payne's ticker and the name of HP INC, ticker HPQ); neither is asserted, `resolved` is false, `match_status` is \"ambiguous\", and both head `alternates`. \"sec_ticker_unchecked\": the string is a ticker symbol, but SEC's registrant-name index did not answer, so whether it is also another registrant's name could not be checked; nothing is asserted, `resolved` is false, `match_status` is \"ambiguous\", the ticker holder is under `cik_withheld`, and a retry completes it."
    • changedOutput schema / properties / match_basis / enum
      Previous value: -[
      -  "sec_ticker",
      -  "sec_ticker_word",
      -  "sec_name",
      -  "sec_cik",
      -  "sec_ticker_rival_name"
      -]New value: +[
      +  "sec_ticker",
      +  "sec_ticker_word",
      +  "sec_name",
      +  "sec_cik",
      +  "sec_ticker_rival_name",
      +  "sec_ticker_unchecked"
      +]
  6. Changed6 schema fields changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "type": "company",
      -    "value": "AAPL"
      -  }
      -]New value: +[
      +  {
      +    "type": "company",
      +    "value": "AAPL"
      +  },
      +  {
      +    "type": "company",
      +    "value": "0000320193"
      +  }
      +]
    • addedOutput schema / properties / alternates
      Added value: +{
      +  "description": "Entities that share the typed string with the entity in `ids`, in ONE fixed order for the same input (SEC registrants first when the basis is \"sec_ticker_rival_name\", then register rows by score, register_key, register_id), slimmed to who and where (the full rows are in `candidates`). For an exact ticker they are lookalikes of the symbol and do not make the answer ambiguous; for \"sec_ticker_word\" and \"sec_name\" they are the rivals the registers hold.",
      +  "items": {
      +    "properties": {
      +      "basis": {
      +        "description": "Only on the two SEC rows of a \"sec_ticker_rival_name\" answer: which claim this registrant has on the string, the ticker or the name.",
      +        "enum": [
      +          "sec_ticker",
      +          "sec_name"
      +        ],
      +        "type": "string"
      +      },
      +      "cik": {
      +        "type": "string"
      +      },
      +      "company_name": {
      +        "type": "string"
      +      },
      +      "country": {
      +        "type": "string"
      +      },
      +      "legal_name": {
      +        "type": "string"
      +      },
      +      "register": {
      +        "type": "string"
      +      },
      +      "register_id": {
      +        "type": "string"
      +      },
      +      "register_key": {
      +        "type": "string"
      +      },
      +      "score": {
      +        "type": "number"
      +      },
      +      "status": {
      +        "type": "string"
      +      },
      +      "ticker": {
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / match_basis
      Added value: +{
      +  "description": "What `ids.cik` rests on, present whenever a CIK is asserted or withheld on this basis. \"sec_ticker\": the typed string is exactly the ticker symbol of one listed security, and it is not also the issuer's own first word; this settles the answer whatever the registers hold. \"sec_ticker_word\": also a ticker, but the typed word is the start of the issuer's name (Bolt, Uber), so register entities with that name are real rivals. \"sec_name\": a name match in SEC's company list. \"sec_cik\": the caller supplied the CIK. \"sec_ticker_rival_name\": the string is the ticker of one SEC registrant AND the name of a different one (HP is Helmerich & Payne's ticker and the name of HP INC, ticker HPQ); neither is asserted, `resolved` is false, `match_status` is \"ambiguous\", and both head `alternates`.",
      +  "enum": [
      +    "sec_ticker",
      +    "sec_ticker_word",
      +    "sec_name",
      +    "sec_cik",
      +    "sec_ticker_rival_name"
      +  ],
      +  "type": "string"
      +}
    • changedOutput schema / properties / match_status / description
      Previous value: -"The headline to branch on. \"ambiguous\" is an ANSWER, not a failure: two companies matched the name equally well and both are in `candidates`. \"no_match\" means every register in `searched` was asked and none carried it. \"incomplete\" means one of them could NOT be asked (it carries an `error` in `searched[]`), so the candidate set is short by an unknown amount and no id is asserted, distinct from \"ambiguous\" because a RETRY is what resolves it, not a narrower query; `fanout_incomplete` names the unreachable registers and carries, under `withheld_match`, the candidate that would have been returned on a complete fan-out."New value: +"The headline to branch on. \"matched\" is ONE entity: a national-register match, or, when `match_basis` is \"sec_ticker\", a typed string that is exactly the ticker symbol of one listed security (the register search's own verdict is then kept in `register_match_status` and its lookalikes in `alternates`). \"ambiguous\" is an ANSWER, not a failure: two companies matched the name equally well and both are in `candidates`. \"no_match\" means every register in `searched` was asked and none carried it. \"incomplete\" means one of them could NOT be asked (it carries an `error` in `searched[]`), so the candidate set is short by an unknown amount and no id is asserted, distinct from \"ambiguous\" because a RETRY is what resolves it, not a narrower query; `fanout_incomplete` names the unreachable registers and carries, under `withheld_match`, the candidate that would have been returned on a complete fan-out."
    • addedOutput schema / properties / register_match_status
      Added value: +{
      +  "description": "Present only when `match_status` was settled by an exact ticker rather than by the registers: the register search's own verdict, verbatim. It never changes which security the ticker names.",
      +  "enum": [
      +    "matched",
      +    "ambiguous",
      +    "no_match",
      +    "incomplete"
      +  ],
      +  "type": "string"
      +}
    • changedOutput schema / properties / resolved / description
      Previous value: -"At least one identifier was established. Read `match_status` and `unresolved` for WHICH, a company can be resolved in a national register with no CIK at all."New value: +"At least one identifier was established. Read `match_basis` for WHAT the ids rest on and `unresolved` for what is missing; a company can be resolved in a national register with no CIK at all. When `match_status` is \"matched\" this is true. `resolved: true` with `match_status: \"ambiguous\"` is the one residual combination and it means exactly this: SEC named ONE filer on an exact hit that is also a name or word (`match_basis` \"sec_ticker_word\" or \"sec_name\", e.g. \"Bolt\", \"Zoom\"), and the registers hold rivals with the same name, listed under `alternates`. An exact ticker symbol (\"AAPL\") is never in that state, and a ticker that is also the name of a DIFFERENT registrant (\"HP\") is `resolved: false` with `match_basis` \"sec_ticker_rival_name\"."
  7. Changed14 schema fields changed
    • changedInput schema / properties / country / description
      Previous value: -"OPTIONAL ISO 3166-1 alpha-2 of the country whose business register you mean (\"NO\", \"FI\", \"JP\", \"GB\", \"FR\", \"EE\", \"BR\"). Narrows the national-register fan-out and is often the difference between the right company and a US namesake — \"Apple\" with country \"NO\" is a Norwegian company, not Apple Inc. Omitting it searches every register we can name, which is the right default when you do not know. company only; ignored for drug."New value: +"OPTIONAL ISO 3166-1 alpha-2 of the country whose business register you mean (\"NO\", \"FI\", \"JP\", \"GB\", \"FR\", \"EE\", \"BR\"). Narrows the national-register fan-out and is often the difference between the right company and a US namesake, \"Apple\" with country \"NO\" is a Norwegian company, not Apple Inc. Omitting it searches every register we can name, which is the right default when you do not know. company only; ignored for drug."
    • changedInput schema / properties / value / description
      Previous value: -"For company: ticker (AAPL), CIK (0000320193), or name. For drug: brand or generic name (e.g., \"ozempic\", \"metformin\"). Pass the ENTITY NAME ONLY — for a bond that is the ISSUER exactly as printed (\"NEW YORK ST DORM AUTH\"), never the question's full noun phrase (\"NEW YORK ST DORM AUTH revenue bonds\"): the FIGI lookup matches instrument names, so trailing security-class words match nothing."New value: +"For company: ticker (AAPL), CIK (0000320193), or name. For drug: brand or generic name (e.g., \"ozempic\", \"metformin\"). Pass the ENTITY NAME ONLY, for a bond that is the ISSUER exactly as printed (\"NEW YORK ST DORM AUTH\"), never the question's full noun phrase (\"NEW YORK ST DORM AUTH revenue bonds\"): the FIGI lookup matches instrument names, so trailing security-class words match nothing."
    • changedOutput schema / properties / candidates / items / properties / registration_status / description
      Previous value: -"GLEIF rows only: the LEI RECORD's lifecycle (ISSUED/LAPSED/RETIRED/...). A DIFFERENT fact from `status` — a lapsed LEI is unmaintained reference data about a company that may well still trade."New value: +"GLEIF rows only: the LEI RECORD's lifecycle (ISSUED/LAPSED/RETIRED/...). A DIFFERENT fact from `status`, a lapsed LEI is unmaintained reference data about a company that may well still trade."
    • changedOutput schema / properties / fanout_incomplete / description
      Previous value: -"Present IFF at least one register in `searched[]` carried an `error` — set even when `match_status` stayed \"ambiguous\". `withheld_match` is the candidate this call declined to ASSERT because a register was missing, carried rather than discarded so a caller who accepts the caveat can still use it."New value: +"Present IFF at least one register in `searched[]` carried an `error`, set even when `match_status` stayed \"ambiguous\". `withheld_match` is the candidate this call declined to ASSERT because a register was missing, carried rather than discarded so a caller who accepts the caveat can still use it."
    • changedOutput schema / properties / figi_withheld / description
      Previous value: -"A FIGI that is NOT asserted. Either it matched this name in OpenFIGI (`figi_match: \"name_search\"`) while `match_status` is \"incomplete\" — a name search cannot tell a company apart from a security carrying its name, and the registers that would have settled it are the ones we could not ask — or it is a `ticker_map` FIGI whose ticker came from a FUZZY SEC name match that is itself withheld (`cik_withheld`), so the mapping inherits the doubt. A `ticker_map` FIGI from an EXACT SEC hit (a real ticker, a CIK, an exact legal name) is never withheld. Carried so a caller who accepts the caveat can use it; see `unresolved.figi`."New value: +"A FIGI that is NOT asserted. Either it matched this name in OpenFIGI (`figi_match: \"name_search\"`) while `match_status` is \"incomplete\", a name search cannot tell a company apart from a security carrying its name, and the registers that would have settled it are the ones we could not ask, or it is a `ticker_map` FIGI whose ticker came from a FUZZY SEC name match that is itself withheld (`cik_withheld`), so the mapping inherits the doubt. A `ticker_map` FIGI from an EXACT SEC hit (a real ticker, a CIK, an exact legal name) is never withheld. Carried so a caller who accepts the caveat can use it; see `unresolved.figi`."
    • changedOutput schema / properties / ids / description
      Previous value: -"Every identifier established: cik, ticker, company_name, lei, figi, isin, cusip, register_id, register_country. A key absent here appears in `unresolved` with a reason — never silently dropped."New value: +"Every identifier established: cik, ticker, company_name, lei, figi, isin, cusip, register_id, register_country. A key absent here appears in `unresolved` with a reason, never silently dropped."
    • changedOutput schema / properties / match_status / description
      Previous value: -"The headline to branch on. \"ambiguous\" is an ANSWER, not a failure: two companies matched the name equally well and both are in `candidates`. \"no_match\" means every register in `searched` was asked and none carried it. \"incomplete\" means one of them could NOT be asked (it carries an `error` in `searched[]`), so the candidate set is short by an unknown amount and no id is asserted — distinct from \"ambiguous\" because a RETRY is what resolves it, not a narrower query; `fanout_incomplete` names the unreachable registers and carries, under `withheld_match`, the candidate that would have been returned on a complete fan-out."New value: +"The headline to branch on. \"ambiguous\" is an ANSWER, not a failure: two companies matched the name equally well and both are in `candidates`. \"no_match\" means every register in `searched` was asked and none carried it. \"incomplete\" means one of them could NOT be asked (it carries an `error` in `searched[]`), so the candidate set is short by an unknown amount and no id is asserted, distinct from \"ambiguous\" because a RETRY is what resolves it, not a narrower query; `fanout_incomplete` names the unreachable registers and carries, under `withheld_match`, the candidate that would have been returned on a complete fan-out."
    • changedOutput schema / properties / registers / description
      Previous value: -"The matched entity as every register that carries it — the match (flagged `matched: true`) plus anything that collapsed into it. A Companies House number AND the LEI that crosswalks to it are the SAME answer, not rivals."New value: +"The matched entity as every register that carries it, the match (flagged `matched: true`) plus anything that collapsed into it. A Companies House number AND the LEI that crosswalks to it are the SAME answer, not rivals."
    • changedOutput schema / properties / registers / items / properties / registration_status / description
      Previous value: -"GLEIF rows only: the LEI RECORD's lifecycle (ISSUED/LAPSED/RETIRED/...). A DIFFERENT fact from `status` — a lapsed LEI is unmaintained reference data about a company that may well still trade."New value: +"GLEIF rows only: the LEI RECORD's lifecycle (ISSUED/LAPSED/RETIRED/...). A DIFFERENT fact from `status`, a lapsed LEI is unmaintained reference data about a company that may well still trade."
    • changedOutput schema / properties / related / items / properties / registration_status / description
      Previous value: -"GLEIF rows only: the LEI RECORD's lifecycle (ISSUED/LAPSED/RETIRED/...). A DIFFERENT fact from `status` — a lapsed LEI is unmaintained reference data about a company that may well still trade."New value: +"GLEIF rows only: the LEI RECORD's lifecycle (ISSUED/LAPSED/RETIRED/...). A DIFFERENT fact from `status`, a lapsed LEI is unmaintained reference data about a company that may well still trade."
    • changedOutput schema / properties / resolved / description
      Previous value: -"At least one identifier was established. Read `match_status` and `unresolved` for WHICH — a company can be resolved in a national register with no CIK at all."New value: +"At least one identifier was established. Read `match_status` and `unresolved` for WHICH, a company can be resolved in a national register with no CIK at all."
    • changedOutput schema / properties / searched / description
      Previous value: -"EVERY register asked, with its own as-of date and row count. A register that could not be reached carries `error` — 0 rows with an error is \"we could not ask\", 0 rows without one is \"nothing is there\", and they are different answers."New value: +"EVERY register asked, with its own as-of date and row count. A register that could not be reached carries `error`, 0 rows with an error is \"we could not ask\", 0 rows without one is \"nothing is there\", and they are different answers."
    • changedOutput schema / properties / sec_alternatives / description
      Previous value: -"EDGAR's other name-matching candidates: distinct companies, deduped by CIK, excluding this issuer's own share classes — surfaced instead of dropped so a caller can tell a genuinely CONTESTED name match from a clean one."New value: +"EDGAR's other name-matching candidates: distinct companies, deduped by CIK, excluding this issuer's own share classes, surfaced instead of dropped so a caller can tell a genuinely CONTESTED name match from a clean one."
    • changedOutput schema / properties / unresolved / description
      Previous value: -"Per-identifier reason an id could NOT be established — the honest twin of `ids`."New value: +"Per-identifier reason an id could NOT be established, the honest twin of `ids`."
  8. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description goes well beyond them: graceful degradation when GLEIF/OpenFIGI is down, ambiguity handled by returning `figi_candidates` rather than guessing, and unresolved identifiers surfaced under `unresolved` instead of omitted. It also discloses that each call cascades through several internal endpoints.

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

Conciseness2/5

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

The use-case prelude is well front-loaded, but the "company" block is a single run-on sentence with deeply nested parentheticals covering FIGI search, bonds, ISIN→LEI, source labelling and the `unresolved` field. Much of that content duplicates the schema, so the length is not earning its place.

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?

An output schema exists, but the description still helpfully explains the non-obvious return shapes (`figi_candidates`, `unresolved`, source-labelled identifiers). Coverage of input types, degradation behavior, and ambiguity handling makes it complete for a multi-source resolver.

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

Parameters3/5

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

Schema coverage is 100% and the per-property descriptions already contain the CIK-format rules, the bare-number ambiguity warnings, and the country-narrowing semantics. The description's parameter prose largely restates that, so it adds little beyond the schema; the baseline of 3 for fully documented params is appropriate.

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 opening line states a specific verb (resolve) against a specific resource (a user-spoken name → canonical identifiers) and lists concrete phrasings that trigger it. It also scopes the output types (CIK, ticker, LEI, FIGI, RxCUI, company_name), so an agent can tell it apart from entity_profile or company_facts without inspecting either schema.

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?

"Use FIRST whenever you have a name but need an ID" is an explicit routing rule, and the closing note ("replaces 2-3 manual lookups") gives the cost tradeoff. Supported types and the company-vs-drug split are enumerated, so the agent knows which `type` value to pick and when this tool is the right entry point.

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.