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, 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" or "drug".
valueYesFor 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.
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. 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
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.
ingredientNo
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_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.
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. 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.
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.
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. 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"
      +]
  2. Changed8 schema fields changed
    • changedOutput schema / properties / alternates / description
      Previous value: -"Register entities that share the typed string with the entity in `ids`, 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."New value: +"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."
    • addedOutput schema / properties / alternates / items / properties / basis
      Added value: +{
      +  "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"
      +}
    • addedOutput schema / properties / alternates / items / properties / cik
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / alternates / items / properties / company_name
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / alternates / items / properties / ticker
      Added value: +{
      +  "type": "string"
      +}
    • changedOutput schema / properties / match_basis / description
      Previous value: -"What `ids.cik` rests on, present whenever a CIK is asserted. \"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."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`."
    • changedOutput schema / properties / match_basis / enum
      Previous value: -[
      -  "sec_ticker",
      -  "sec_ticker_word",
      -  "sec_name",
      -  "sec_cik"
      -]New value: +[
      +  "sec_ticker",
      +  "sec_ticker_word",
      +  "sec_name",
      +  "sec_cik",
      +  "sec_ticker_rival_name"
      +]
    • changedOutput schema / properties / resolved / description
      Previous 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."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\"."
  3. Changed18 schema fields changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "type": "company",
      -    "value": "AAPL"
      -  }
      -]New value: +[
      +  {
      +    "type": "company",
      +    "value": "AAPL"
      +  },
      +  {
      +    "type": "company",
      +    "value": "0000320193"
      +  }
      +]
    • 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."
    • addedOutput schema / properties / alternates
      Added value: +{
      +  "description": "Register entities that share the typed string with the entity in `ids`, 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": {
      +      "country": {
      +        "type": "string"
      +      },
      +      "legal_name": {
      +        "type": "string"
      +      },
      +      "register": {
      +        "type": "string"
      +      },
      +      "register_id": {
      +        "type": "string"
      +      },
      +      "register_key": {
      +        "type": "string"
      +      },
      +      "score": {
      +        "type": "number"
      +      },
      +      "status": {
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • 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."
    • addedOutput schema / properties / match_basis
      Added value: +{
      +  "description": "What `ids.cik` rests on, present whenever a CIK is asserted. \"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.",
      +  "enum": [
      +    "sec_ticker",
      +    "sec_ticker_word",
      +    "sec_name",
      +    "sec_cik"
      +  ],
      +  "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 / 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_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."
    • 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`."
  4. Changed3 schema fields changed
    • changedOutput schema / properties / candidates / items / properties / detail_tool / description
      Previous value: -"The live pack tool that returns the full record, e.g. \"brreg-no:get_entity\"."New value: +"The live pack tool that returns the full record, e.g. \"brreg-no:brreg_no_get_entity\"."
    • changedOutput schema / properties / registers / items / properties / detail_tool / description
      Previous value: -"The live pack tool that returns the full record, e.g. \"brreg-no:get_entity\"."New value: +"The live pack tool that returns the full record, e.g. \"brreg-no:brreg_no_get_entity\"."
    • changedOutput schema / properties / related / items / properties / detail_tool / description
      Previous value: -"The live pack tool that returns the full record, e.g. \"brreg-no:get_entity\"."New value: +"The live pack tool that returns the full record, e.g. \"brreg-no:brreg_no_get_entity\"."
  5. Changed1 schema field changed
    • changedOutput schema / properties / sec_alternatives / description
      Previous value: -"EDGAR's own discarded near-misses on a name match, surfaced instead of dropped."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."
  6. Changed5 schema fields changed
    • 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. 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. See `unresolved.cik` for the reason."
    • addedOutput schema / properties / company_name_withheld
      Added value: +{
      +  "description": "The company name of a FUZZY SEC name match that is NOT asserted, withheld together with `cik_withheld`. See `unresolved.cik`.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / figi_withheld / description
      Previous value: -"A FIGI that matched this name in OpenFIGI (`figi_match: \"name_search\"`) and is NOT asserted, because `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. A `ticker_map` FIGI is never withheld this way — it is corroborated by the resolved ticker it came from. Carried so a caller who accepts the caveat can use it; see `unresolved.figi`, and retry, since a transiently rate-limited register completes on the next call."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`."
    • addedOutput schema / properties / lei_withheld
      Added value: +{
      +  "description": "A 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`.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / ticker_withheld
      Added value: +{
      +  "description": "The 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`.",
      +  "type": "string"
      +}
  7. Changed2 schema fields changed
    • addedInput schema / properties / country
      Added value: +{
      +  "description": "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.",
      +  "type": "string"
      +}
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "brand": {
      +      "type": "string"
      +    },
      +    "candidates": {
      +      "description": "Rivals, best first. Populated on \"ambiguous\" and on \"matched\" alike.",
      +      "items": {
      +        "properties": {
      +          "country": {
      +            "description": "ISO-2 of the REGISTER, not of the company's operations.",
      +            "type": "string"
      +          },
      +          "data_as_of": {
      +            "description": "That register's own snapshot date, per row, so a stale country is visible.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "detail_tool": {
      +            "description": "The live pack tool that returns the full record, e.g. \"brreg-no:get_entity\".",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "legal_form": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "legal_name": {
      +            "type": "string"
      +          },
      +          "lei": {
      +            "description": "From the GLEIF crosswalk when present. Never guessed from a name.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "match_type": {
      +            "enum": [
      +              "id",
      +              "exact",
      +              "exact_form",
      +              "prefix",
      +              "tokens"
      +            ],
      +            "type": "string"
      +          },
      +          "matched_kind": {
      +            "enum": [
      +              "legal",
      +              "trading",
      +              "former",
      +              "english",
      +              "kana"
      +            ],
      +            "type": "string"
      +          },
      +          "matched_name": {
      +            "description": "The name row that matched, exactly as the publisher spells it.",
      +            "type": "string"
      +          },
      +          "register": {
      +            "description": "Publisher + dataset, e.g. \"Brønnøysund Register Centre, Enhetsregisteret\". Never a URL or filename.",
      +            "type": "string"
      +          },
      +          "register_id": {
      +            "description": "The native id in the register's own canonical formatting.",
      +            "type": "string"
      +          },
      +          "register_key": {
      +            "description": "Stable machine slug for the register.",
      +            "type": "string"
      +          },
      +          "registration_status": {
      +            "description": "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.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "score": {
      +            "description": "0-1, assigned centrally. An adapter never grades itself.",
      +            "type": "number"
      +          },
      +          "status": {
      +            "description": "The COMPANY's status.",
      +            "enum": [
      +              "active",
      +              "inactive",
      +              "dissolved",
      +              "unknown"
      +            ],
      +            "type": "string"
      +          },
      +          "status_raw": {
      +            "description": "The register's own status word, verbatim and unglossed.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          }
      +        },
      +        "required": [
      +          "country",
      +          "register",
      +          "register_key",
      +          "register_id",
      +          "legal_name",
      +          "score",
      +          "status"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "cik_withheld": {
      +      "description": "A CIK that came back from a FUZZY SEC name match and is NOT asserted, because the spine matched a stronger non-US candidate. 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.",
      +      "type": "string"
      +    },
      +    "fanout_incomplete": {
      +      "description": "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.",
      +      "properties": {
      +        "unavailable": {
      +          "items": {
      +            "properties": {
      +              "country": {
      +                "type": "string"
      +              },
      +              "error": {
      +                "type": "string"
      +              },
      +              "register": {
      +                "type": "string"
      +              },
      +              "register_key": {
      +                "type": "string"
      +              }
      +            },
      +            "type": "object"
      +          },
      +          "type": "array"
      +        },
      +        "withheld_match": {
      +          "type": [
      +            "object",
      +            "null"
      +          ]
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "figi_withheld": {
      +      "description": "A FIGI that matched this name in OpenFIGI (`figi_match: \"name_search\"`) and is NOT asserted, because `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. A `ticker_map` FIGI is never withheld this way — it is corroborated by the resolved ticker it came from. Carried so a caller who accepts the caveat can use it; see `unresolved.figi`, and retry, since a transiently rate-limited register completes on the next call.",
      +      "type": "string"
      +    },
      +    "ids": {
      +      "description": "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.",
      +      "type": "object"
      +    },
      +    "ingredient": {
      +      "type": "string"
      +    },
      +    "match_explanation": {
      +      "description": "Plain words. Always present when the spine ran, and required on \"ambiguous\" and \"no_match\".",
      +      "type": "string"
      +    },
      +    "match_scoring": {
      +      "description": "The margin rule's own inputs, so a caller can see WHY it fell where it did.",
      +      "properties": {
      +        "margin": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "runner_up": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "thresholds": {
      +          "properties": {
      +            "floor": {
      +              "type": "number"
      +            },
      +            "margin": {
      +              "type": "number"
      +            },
      +            "match": {
      +              "type": "number"
      +            }
      +          },
      +          "type": "object"
      +        },
      +        "top": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "match_status": {
      +      "description": "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.",
      +      "enum": [
      +        "matched",
      +        "ambiguous",
      +        "no_match",
      +        "incomplete"
      +      ],
      +      "type": "string"
      +    },
      +    "notes": {
      +      "type": "string"
      +    },
      +    "query": {
      +      "type": "string"
      +    },
      +    "registers": {
      +      "description": "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.",
      +      "items": {
      +        "properties": {
      +          "country": {
      +            "description": "ISO-2 of the REGISTER, not of the company's operations.",
      +            "type": "string"
      +          },
      +          "data_as_of": {
      +            "description": "That register's own snapshot date, per row, so a stale country is visible.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "detail_tool": {
      +            "description": "The live pack tool that returns the full record, e.g. \"brreg-no:get_entity\".",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "legal_form": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "legal_name": {
      +            "type": "string"
      +          },
      +          "lei": {
      +            "description": "From the GLEIF crosswalk when present. Never guessed from a name.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "match_type": {
      +            "enum": [
      +              "id",
      +              "exact",
      +              "exact_form",
      +              "prefix",
      +              "tokens"
      +            ],
      +            "type": "string"
      +          },
      +          "matched_kind": {
      +            "enum": [
      +              "legal",
      +              "trading",
      +              "former",
      +              "english",
      +              "kana"
      +            ],
      +            "type": "string"
      +          },
      +          "matched_name": {
      +            "description": "The name row that matched, exactly as the publisher spells it.",
      +            "type": "string"
      +          },
      +          "register": {
      +            "description": "Publisher + dataset, e.g. \"Brønnøysund Register Centre, Enhetsregisteret\". Never a URL or filename.",
      +            "type": "string"
      +          },
      +          "register_id": {
      +            "description": "The native id in the register's own canonical formatting.",
      +            "type": "string"
      +          },
      +          "register_key": {
      +            "description": "Stable machine slug for the register.",
      +            "type": "string"
      +          },
      +          "registration_status": {
      +            "description": "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.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "score": {
      +            "description": "0-1, assigned centrally. An adapter never grades itself.",
      +            "type": "number"
      +          },
      +          "status": {
      +            "description": "The COMPANY's status.",
      +            "enum": [
      +              "active",
      +              "inactive",
      +              "dissolved",
      +              "unknown"
      +            ],
      +            "type": "string"
      +          },
      +          "status_raw": {
      +            "description": "The register's own status word, verbatim and unglossed.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          }
      +        },
      +        "required": [
      +          "country",
      +          "register",
      +          "register_key",
      +          "register_id",
      +          "legal_name",
      +          "score",
      +          "status"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "related": {
      +      "description": "Entities that collapsed INTO the match, each carrying `collapsed_by`.",
      +      "items": {
      +        "properties": {
      +          "country": {
      +            "description": "ISO-2 of the REGISTER, not of the company's operations.",
      +            "type": "string"
      +          },
      +          "data_as_of": {
      +            "description": "That register's own snapshot date, per row, so a stale country is visible.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "detail_tool": {
      +            "description": "The live pack tool that returns the full record, e.g. \"brreg-no:get_entity\".",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "legal_form": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "legal_name": {
      +            "type": "string"
      +          },
      +          "lei": {
      +            "description": "From the GLEIF crosswalk when present. Never guessed from a name.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "match_type": {
      +            "enum": [
      +              "id",
      +              "exact",
      +              "exact_form",
      +              "prefix",
      +              "tokens"
      +            ],
      +            "type": "string"
      +          },
      +          "matched_kind": {
      +            "enum": [
      +              "legal",
      +              "trading",
      +              "former",
      +              "english",
      +              "kana"
      +            ],
      +            "type": "string"
      +          },
      +          "matched_name": {
      +            "description": "The name row that matched, exactly as the publisher spells it.",
      +            "type": "string"
      +          },
      +          "register": {
      +            "description": "Publisher + dataset, e.g. \"Brønnøysund Register Centre, Enhetsregisteret\". Never a URL or filename.",
      +            "type": "string"
      +          },
      +          "register_id": {
      +            "description": "The native id in the register's own canonical formatting.",
      +            "type": "string"
      +          },
      +          "register_key": {
      +            "description": "Stable machine slug for the register.",
      +            "type": "string"
      +          },
      +          "registration_status": {
      +            "description": "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.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "score": {
      +            "description": "0-1, assigned centrally. An adapter never grades itself.",
      +            "type": "number"
      +          },
      +          "status": {
      +            "description": "The COMPANY's status.",
      +            "enum": [
      +              "active",
      +              "inactive",
      +              "dissolved",
      +              "unknown"
      +            ],
      +            "type": "string"
      +          },
      +          "status_raw": {
      +            "description": "The register's own status word, verbatim and unglossed.",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          }
      +        },
      +        "required": [
      +          "country",
      +          "register",
      +          "register_key",
      +          "register_id",
      +          "legal_name",
      +          "score",
      +          "status"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "resolved": {
      +      "description": "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.",
      +      "type": "boolean"
      +    },
      +    "resources": {
      +      "type": "object"
      +    },
      +    "searched": {
      +      "description": "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.",
      +      "items": {
      +        "properties": {
      +          "country": {
      +            "type": "string"
      +          },
      +          "data_as_of": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "error": {
      +            "type": "string"
      +          },
      +          "register": {
      +            "type": "string"
      +          },
      +          "register_key": {
      +            "type": "string"
      +          },
      +          "rows": {
      +            "type": "number"
      +          }
      +        },
      +        "required": [
      +          "register",
      +          "register_key",
      +          "country",
      +          "rows"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "sec_alternatives": {
      +      "description": "EDGAR's own discarded near-misses on a name match, surfaced instead of dropped.",
      +      "items": {
      +        "properties": {
      +          "cik": {
      +            "type": "string"
      +          },
      +          "company_name": {
      +            "type": "string"
      +          },
      +          "ticker": {
      +            "type": "string"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "sources": {
      +      "description": "Per-identifier provenance. Every key in `ids` has a matching key here.",
      +      "type": "object"
      +    },
      +    "type": {
      +      "type": "string"
      +    },
      +    "unresolved": {
      +      "description": "Per-identifier reason an id could NOT be established — the honest twin of `ids`.",
      +      "type": "object"
      +    }
      +  },
      +  "required": [
      +    "type",
      +    "query",
      +    "resolved",
      +    "ids",
      +    "sources",
      +    "unresolved"
      +  ],
      +  "type": "object"
      +}
  8. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "type": "company",
      +    "value": "AAPL"
      +  }
      +]
  9. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the bar is lower, yet the description adds real behavior: graceful degradation when GLEIF/OpenFIGI are down, per-identifier source attribution, explicit `unresolved` reporting instead of silent omission, and `figi_candidates` on ambiguous issuer matches. Slightly held back because it never says how large the internal cascade is or whether there are latency/rate limits worth knowing.

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

Conciseness3/5

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

Front-loading with quoted user phrasings is useful, but the body is one enormous run-on sentence nesting CIK/LEI/FIGI sub-cases, and the closing line ('using resolve_entity replaces 2-3 manual lookups') is ungrammatical and redundant with the earlier cascade statement. Structure could be broken into scannable clauses without losing content.

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 multi-source resolution tool with three parameters and a declared output schema, the description covers input types, fallback behavior, ambiguity handling and failure reporting. An agent has everything needed to call it correctly and interpret the result.

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 schema coverage at 100% the baseline is 3, but the description adds meaning the schema does not: that `value` also accepts an ISIN (resolved to the legal entity via GLEIF ISIN-to-LEI), and that the trade-off of omitting `country` is a full multi-register fan-out. It reinforces rather than merely restates the schema.

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?

States a specific verb (resolve) and resource (a user-spoken name) plus the exact output (canonical identifiers other tools require), and enumerates the two supported entity types with what each returns. An agent can tell this apart from lookup siblings like company_facts or company_register_search without opening a 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?

Gives an explicit routing rule ('Use FIRST whenever you have a name but need an ID') and maps concrete user phrasings (ticker, CIK, LEI, RxCUI, 'who owns X') to the tool. It also explains the company-vs-drug choice and when to supply country versus omit it.

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.