Skip to main content
Glama

sanctions-screening-mcp-server

sanctions-screening-mcp-server: screen name

sanctions_screen_name
Read-onlyIdempotent

Screen a name (person, company, vessel, aircraft) against loaded sanctions and export-control watchlists — OFAC SDN + Consolidated, EU, UK, UN, and the six BIS/State CSL lists — alias- and fuzzy-aware. Check sanctions_list_sources for coverage before interpreting an empty result; zero-record CSL lists are not loaded. Returns scored potential matches with the source list, sanctioning program, designation date, and the matched alias; an OFAC party both OFAC lists publish under one entry ID is one hit, its sources naming both lists. Strict mode (default) matches exact-normalized then all-tokens-present, a legal form matching any spelling of the same form (Ltd and Limited, LLC and OOO), then runs a fuzzy pass over each selected list strict finds nothing on, and over the UK and UN lists either way for a name holding a letter outside the Latin script: a full pass when strict finds nothing on any list, otherwise one that adds only candidates covering every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf, by spelling or by sound, ranked after the strict hits. Fuzzy mode runs the fuzzy pass over every selected list. It adds Jaro-Winkler and phonetic matching and labels hits approximate with a raw 0–1 similarity score plus the count of query tokens the candidate covers, which orders candidates that tie on score; fuzzySources names the lists it searched. Results are paged: totalAvailable and hasMore report matches beyond the returned page, and nextOffset retrieves them. This is a screening AID for a human/compliance review, NOT a compliance determination: a hit means "review this candidate against the official source," and an empty result never means "cleared."

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "sanctions_screen_name"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe name to screen (person, organization, vessel, or aircraft), in any script. It must contain at least one letter or digit, and at most 64 words and 1024 characters.
limitNoMaximum number of potential matches to return in one page. Values above 100 are clamped to 100.
offsetNoZero-based index of the first potential match to return. Re-call with the returned nextOffset to page through every match when hasMore is true; an offset past the end returns an empty page, not an error.
sourcesNoRestrict to specific source lists. Omit to screen all loaded lists.
minScoreNoScore floor for approximate hits (0–1), applied uniformly to every fuzzy candidate regardless of how it was matched (Jaro-Winkler, token, or phonetic); a query token counts toward queryTokenCoverage by spelling only when its match clears it too, and a token matched by sound counts toward coverage without admitting a candidate on its own. It governs every fuzzy pass: fuzzy mode, and in strict mode the pass that follows strict matching, so raising it can remove approximate hits from a strict screen as well. Exact and strong hits are unaffected. Defaults to the server's configured floor.
matchModeNostrict (default): exact-normalized, then all-tokens-present with a legal form matching any spelling of the same form (Ltd and Limited, LLC and OOO), then a fuzzy pass over each selected list strict finds nothing on, and over the UK and UN lists either way for a name holding a letter outside the Latin script — a full pass when strict finds nothing on any list, otherwise adding only candidates that cover every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf, by spelling or by sound. fuzzy: a scored Jaro-Winkler + phonetic pass over every selected list.strict
entityTypeNoRestrict to one entity class, or "any" (default) to screen across all. A class filter excludes records whose known type differs; unknown types remain eligible.any

Output Schema

NameRequiredDescriptionDefault
hitsNoPotential matches, ranked by match type, then score, then how much of the query each candidate explains. Candidates tied on all three are ordered by source list, then entry ID — not by relevance.
errorNoPresent when the call failed. Absent on success.
caveatNoDecision-support caveat — this is a screening aid, not a compliance determination.
noticeNoGuidance when no candidate matched — how to broaden, and what an empty result does NOT mean — when the requested offset sits past the end of the result set, or when the fuzzy pass reached its candidate bound and a more distinctive word would narrow it. It also reports a clamped page limit.
hasMoreNoTrue when the result set holds matches beyond this page — re-call with nextOffset. It describes pages only: false on the last page, whatever totalAvailableBasis says.
nextOffsetNoThe offset to request next. Present only when hasMore is true.
totalCountNoNumber of potential matches returned in this page.
fuzzySourcesNoThe selected lists the fuzzy pass searched, in list order; absent when no fuzzy pass ran. Beside strict hits these are the lists strict found nothing on, plus the UK and UN lists for a name holding a letter outside the Latin script, and only their candidates covering every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf, by spelling or by sound, were added.
matchModeUsedNofuzzy when a full fuzzy pass searched every selected list (fuzzy mode, or a strict screen that found nothing on any list); strict otherwise, including a strict screen completed by a fuzzy pass over its strict-empty lists and, for a name holding a letter outside the Latin script, the UK and UN lists.
totalAvailableNoPotential matches in the result set across all pages, before limit and offset were applied — every one is reachable by paging. An OFAC party both OFAC lists publish counts once.
normalizedQueryNoThe name as the server folded it for matching.
totalAvailableBasisNoHow to read totalAvailable: exact = the complete strict match set, no fuzzy pass having run (fuzzySources is absent); lower_bound = a fuzzy pass ran (fuzzySources is present), which scores only the candidates blocking pooled, so more matches may exist beyond the result set.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • changedInput schema / properties / matchMode / description
      Previous value: -"strict (default): exact-normalized then all-tokens-present, then a fuzzy pass over each selected list strict finds nothing on — a full pass when strict finds nothing on any list, otherwise adding only candidates that cover every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf. fuzzy: a scored Jaro-Winkler + phonetic pass over every selected list."New value: +"strict (default): exact-normalized, then all-tokens-present with a legal form matching any spelling of the same form (Ltd and Limited, LLC and OOO), then a fuzzy pass over each selected list strict finds nothing on, and over the UK and UN lists either way for a name holding a letter outside the Latin script — a full pass when strict finds nothing on any list, otherwise adding only candidates that cover every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf, by spelling or by sound. fuzzy: a scored Jaro-Winkler + phonetic pass over every selected list."
    • changedInput schema / properties / minScore / description
      Previous value: -"Score floor for approximate hits (0–1), applied uniformly to every fuzzy candidate regardless of how it was matched (Jaro-Winkler, token, or phonetic); a query token counts toward queryTokenCoverage only when its match clears it too. It governs every fuzzy pass: fuzzy mode, and in strict mode the pass over the lists strict found nothing on, so raising it can remove approximate hits from a strict screen as well. Exact and strong hits are unaffected. Defaults to the server's configured floor."New value: +"Score floor for approximate hits (0–1), applied uniformly to every fuzzy candidate regardless of how it was matched (Jaro-Winkler, token, or phonetic); a query token counts toward queryTokenCoverage by spelling only when its match clears it too, and a token matched by sound counts toward coverage without admitting a candidate on its own. It governs every fuzzy pass: fuzzy mode, and in strict mode the pass that follows strict matching, so raising it can remove approximate hits from a strict screen as well. Exact and strong hits are unaffected. Defaults to the server's configured floor."
    • changedOutput schema / properties / fuzzySources / description
      Previous value: -"The selected lists the fuzzy pass searched, in list order; absent when no fuzzy pass ran. Beside strict hits these are the lists strict found nothing on, and only their candidates covering every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf were added."New value: +"The selected lists the fuzzy pass searched, in list order; absent when no fuzzy pass ran. Beside strict hits these are the lists strict found nothing on, plus the UK and UN lists for a name holding a letter outside the Latin script, and only their candidates covering every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf, by spelling or by sound, were added."
    • changedOutput schema / properties / hits / items / properties / matchType / description
      Previous value: -"exact = native normalized name equality; strong = all native query tokens present; approximate = fuzzy/phonetic, optionally comparing Russian-alphabet romanizations while retaining the published matchedName."New value: +"exact = native normalized name equality; strong = all native query tokens present, a legal form counting in any spelling of the same form (Ltd and Limited, LLC and OOO; never LLC and Ltd); approximate = fuzzy/phonetic, optionally comparing Russian-alphabet romanizations while retaining the published matchedName."
    • changedOutput schema / properties / hits / items / properties / queryTokenCoverage / description
      Previous value: -"How much of the query this candidate explains, as a literal token count — a second real measurement, never folded into score. It is the tie-break applied after score, because one shared exact token pins several candidates at the same score. Absent for exact/strong hits."New value: +"How much of the query this candidate explains, as a literal token count — a second real measurement, never folded into score. It is the tie-break applied after score, because one shared exact token pins several candidates at the same score; of two equal counts, the one with fewer words matched by sound ranks first. Absent for exact/strong hits."
    • changedOutput schema / properties / hits / items / properties / queryTokenCoverage / properties / covered / description
      Previous value: -"Query tokens individually matched by one of this candidate's tokens at the applied score floor."New value: +"Query tokens individually matched by one of this candidate's tokens: by spelling at the applied score floor, or by sound (counted again in phonetic)."
    • addedOutput schema / properties / hits / items / properties / queryTokenCoverage / properties / phonetic
      Added value: +{
      +  "description": "Of covered, the query tokens matched by sound alone: no candidate token clears the score floor against them, but one shares their primary Double-Metaphone key, at least three characters long (gaddafi and qadhafi, both KTF), and neither word is one of legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf. A sound match never admits a candidate or raises its score. Absent when zero.",
      +  "maximum": 9007199254740991,
      +  "minimum": -9007199254740991,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / hits / items / properties / unReferenceNumber
      Added value: +{
      +  "description": "The UN reference number a UK or EU hit's designation implements, as the list publishes it; absent when it publishes none. Never corrected, and two designations can carry one — a link to check against the un record, not proof of identity.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / matchModeUsed / description
      Previous value: -"fuzzy when every selected list was fuzzy-searched (fuzzy mode, or a strict screen that found nothing on any list); strict otherwise, including a strict screen whose strict-empty lists were completed by a fuzzy pass."New value: +"fuzzy when a full fuzzy pass searched every selected list (fuzzy mode, or a strict screen that found nothing on any list); strict otherwise, including a strict screen completed by a fuzzy pass over its strict-empty lists and, for a name holding a letter outside the Latin script, the UK and UN lists."
    • changedOutput schema / properties / totalAvailableBasis / description
      Previous value: -"How to read totalAvailable: exact = the complete strict match set, strict having found a match on every selected list; lower_bound = a fuzzy pass ran (fuzzySources is present), which scores only the candidates blocking pooled, so more matches may exist beyond the result set."New value: +"How to read totalAvailable: exact = the complete strict match set, no fuzzy pass having run (fuzzySources is absent); lower_bound = a fuzzy pass ran (fuzzySources is present), which scores only the candidates blocking pooled, so more matches may exist beyond the result set."
  2. Changed8 schema fields changed
    • changedInput schema / properties / entityType / description
      Previous value: -"Restrict to one entity class, or \"any\" (default) to screen across all."New value: +"Restrict to one entity class, or \"any\" (default) to screen across all. A class filter excludes records whose known type differs; unknown types remain eligible."
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum number of potential matches to return in one page."New value: +"Maximum number of potential matches to return in one page. Values above 100 are clamped to 100."
    • changedInput schema / properties / limit / maximum
      Previous value: -100New value: +9007199254740991
    • addedOutput schema / properties / hits / items / properties / addressCountries
      Added value: +{
      +  "description": "Distinct countries from published addresses on the source record, omitted when absent.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / hits / items / properties / birthDates
      Added value: +{
      +  "description": "Birth dates from the source record, omitted when none are published.",
      +  "items": {
      +    "additionalProperties": false,
      +    "description": "One published birth date.",
      +    "properties": {
      +      "circa": {
      +        "const": true,
      +        "description": "Present when the source marks the date approximate.",
      +        "type": "boolean"
      +      },
      +      "date": {
      +        "description": "Stored birth date with its original precision or range.",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "date"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / hits / items / properties / designationDate / description
      Previous value: -"The source's own designation date as YYYY-MM-DD; absent when unpublished. For an OFAC party both OFAC lists publish, the date of the source record: each OFAC file dates the party from its own lists, so the two often differ, and sanctions_get_designation under the other list returns that record's date."New value: +"Designation date in YYYY-MM-DD when known to day precision, or published date text otherwise; absent when unpublished. For grouped OFAC parties, this is the source record's date; sanctions_get_designation under the other list returns that record's date."
    • addedOutput schema / properties / hits / items / properties / nationalities
      Added value: +{
      +  "description": "Published nationalities from the source record, omitted when absent.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance when no candidate matched — how to broaden, and what an empty result does NOT mean — when the requested offset sits past the end of the result set, or when the fuzzy pass reached its candidate bound and a more distinctive word would narrow it."New value: +"Guidance when no candidate matched — how to broaden, and what an empty result does NOT mean — when the requested offset sits past the end of the result set, or when the fuzzy pass reached its candidate bound and a more distinctive word would narrow it. It also reports a clamped page limit."
  3. Changed4 schema fields changed
    • changedInput schema / properties / sources / items / enum
      Previous value: -[
      -  "ofac_sdn",
      -  "ofac_consolidated",
      -  "eu",
      -  "uk",
      -  "un"
      -]New value: +[
      +  "ofac_sdn",
      +  "ofac_consolidated",
      +  "eu",
      +  "uk",
      +  "un",
      +  "bis_el",
      +  "bis_dpl",
      +  "bis_uvl",
      +  "bis_meu",
      +  "state_dtc",
      +  "state_acn"
      +]
    • changedOutput schema / properties / fuzzySources / items / enum
      Previous value: -[
      -  "ofac_sdn",
      -  "ofac_consolidated",
      -  "eu",
      -  "uk",
      -  "un"
      -]New value: +[
      +  "ofac_sdn",
      +  "ofac_consolidated",
      +  "eu",
      +  "uk",
      +  "un",
      +  "bis_el",
      +  "bis_dpl",
      +  "bis_uvl",
      +  "bis_meu",
      +  "state_dtc",
      +  "state_acn"
      +]
    • changedOutput schema / properties / hits / items / properties / source / enum
      Previous value: -[
      -  "ofac_sdn",
      -  "ofac_consolidated",
      -  "eu",
      -  "uk",
      -  "un"
      -]New value: +[
      +  "ofac_sdn",
      +  "ofac_consolidated",
      +  "eu",
      +  "uk",
      +  "un",
      +  "bis_el",
      +  "bis_dpl",
      +  "bis_uvl",
      +  "bis_meu",
      +  "state_dtc",
      +  "state_acn"
      +]
    • changedOutput schema / properties / hits / items / properties / sources / items / enum
      Previous value: -[
      -  "ofac_sdn",
      -  "ofac_consolidated",
      -  "eu",
      -  "uk",
      -  "un"
      -]New value: +[
      +  "ofac_sdn",
      +  "ofac_consolidated",
      +  "eu",
      +  "uk",
      +  "un",
      +  "bis_el",
      +  "bis_dpl",
      +  "bis_uvl",
      +  "bis_meu",
      +  "state_dtc",
      +  "state_acn"
      +]
  4. Changed2 schema fields changed
    • changedOutput schema / properties / hits / items / properties / matchType / description
      Previous value: -"exact = normalized name equality; strong = all query tokens present; approximate = fuzzy/phonetic."New value: +"exact = native normalized name equality; strong = all native query tokens present; approximate = fuzzy/phonetic, optionally comparing Russian-alphabet romanizations while retaining the published matchedName."
    • changedOutput schema / properties / hits / items / properties / score / description
      Previous value: -"Raw Jaro-Winkler similarity (0–1) for approximate hits only — a real measurement, not a confidence verdict. Absent for exact/strong hits."New value: +"Raw Jaro-Winkler similarity (0–1) for approximate hits only, measured on native or Russian-alphabet romanized comparison forms — not a confidence verdict or an official alias. Absent for exact/strong hits."
  5. Changed13 schema fields changed
    • changedInput schema / properties / matchMode / description
      Previous value: -"strict (default): exact-normalized then all-tokens-present. fuzzy: also scored Jaro-Winkler + phonetic. Strict auto-falls-back to fuzzy when it finds nothing."New value: +"strict (default): exact-normalized then all-tokens-present, then a fuzzy pass over each selected list strict finds nothing on — a full pass when strict finds nothing on any list, otherwise adding only candidates that cover every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf. fuzzy: a scored Jaro-Winkler + phonetic pass over every selected list."
    • changedInput schema / properties / minScore / description
      Previous value: -"Score floor for fuzzy hits (0–1), applied uniformly to every fuzzy candidate regardless of how it was matched (Jaro-Winkler, token, or phonetic). No hit below this score is returned. Applies to fuzzy mode only; defaults to the server's configured floor."New value: +"Score floor for approximate hits (0–1), applied uniformly to every fuzzy candidate regardless of how it was matched (Jaro-Winkler, token, or phonetic); a query token counts toward queryTokenCoverage only when its match clears it too. It governs every fuzzy pass: fuzzy mode, and in strict mode the pass over the lists strict found nothing on, so raising it can remove approximate hits from a strict screen as well. Exact and strong hits are unaffected. Defaults to the server's configured floor."
    • addedOutput schema / properties / fuzzySources
      Added value: +{
      +  "description": "The selected lists the fuzzy pass searched, in list order; absent when no fuzzy pass ran. Beside strict hits these are the lists strict found nothing on, and only their candidates covering every word of the name other than legal forms, articles and other function words, and the jurisdiction codes uk, usa, uae, and rf were added.",
      +  "items": {
      +    "enum": [
      +      "ofac_sdn",
      +      "ofac_consolidated",
      +      "eu",
      +      "uk",
      +      "un"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / hasMore / description
      Previous value: -"True when potential matches remain beyond this page — re-call with nextOffset."New value: +"True when the result set holds matches beyond this page — re-call with nextOffset. It describes pages only: false on the last page, whatever totalAvailableBasis says."
    • changedOutput schema / properties / hits / description
      Previous value: -"Potential matches, ranked by match type, then score, then how much of the query each candidate explains."New value: +"Potential matches, ranked by match type, then score, then how much of the query each candidate explains. Candidates tied on all three are ordered by source list, then entry ID — not by relevance."
    • changedOutput schema / properties / hits / items / properties / designationDate / description
      Previous value: -"The source's own designation date as YYYY-MM-DD; absent when unpublished."New value: +"The source's own designation date as YYYY-MM-DD; absent when unpublished. For an OFAC party both OFAC lists publish, the date of the source record: each OFAC file dates the party from its own lists, so the two often differ, and sanctions_get_designation under the other list returns that record's date."
    • changedOutput schema / properties / hits / items / properties / source / description
      Previous value: -"Which watchlist this candidate is on — its provenance."New value: +"The watchlist whose record this hit's fields come from — its provenance. For an OFAC party both OFAC lists publish, ofac_sdn unless the Consolidated record matched alone or better; sources names every list."
    • addedOutput schema / properties / hits / items / properties / sources
      Added value: +{
      +  "description": "Every screened list this candidate is on, in list order: one list, or ofac_sdn and ofac_consolidated together for an OFAC party both OFAC lists publish under one entry ID — one hit, not two. Read this, not source, for every list; the entry ID resolves in sanctions_get_designation under each.",
      +  "items": {
      +    "enum": [
      +      "ofac_sdn",
      +      "ofac_consolidated",
      +      "eu",
      +      "uk",
      +      "un"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / hits / items / required
      Previous value: -[
      -  "source",
      -  "sourceLabel",
      -  "sourceEntryId",
      -  "entityType",
      -  "primaryName",
      -  "matchedName",
      -  "matchedNameType",
      -  "matchType"
      -]New value: +[
      +  "source",
      +  "sourceLabel",
      +  "sourceEntryId",
      +  "sources",
      +  "entityType",
      +  "primaryName",
      +  "matchedName",
      +  "matchedNameType",
      +  "matchType"
      +]
    • changedOutput schema / properties / matchModeUsed / description
      Previous value: -"The match mode actually applied (strict may auto-upgrade to fuzzy on empty)."New value: +"fuzzy when every selected list was fuzzy-searched (fuzzy mode, or a strict screen that found nothing on any list); strict otherwise, including a strict screen whose strict-empty lists were completed by a fuzzy pass."
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance when no candidate matched — how to broaden, and what an empty result does NOT mean — or when the requested offset sits past the end of the result set."New value: +"Guidance when no candidate matched — how to broaden, and what an empty result does NOT mean — when the requested offset sits past the end of the result set, or when the fuzzy pass reached its candidate bound and a more distinctive word would narrow it."
    • changedOutput schema / properties / totalAvailable / description
      Previous value: -"Potential matches available across all pages, before limit and offset were applied."New value: +"Potential matches in the result set across all pages, before limit and offset were applied — every one is reachable by paging. An OFAC party both OFAC lists publish counts once."
    • changedOutput schema / properties / totalAvailableBasis / description
      Previous value: -"How to read totalAvailable: exact = the complete strict match set; lower_bound = a bounded scan produced it (every fuzzy pass, and any strict pass that hit the raw-row scan cap), so more may exist."New value: +"How to read totalAvailable: exact = the complete strict match set, strict having found a match on every selected list; lower_bound = a fuzzy pass ran (fuzzySources is present), which scores only the candidates blocking pooled, so more matches may exist beyond the result set."
  6. Changed2 schema fields changed
    • changedOutput schema / properties / hits / items / properties / designationDate / description
      Previous value: -"Designation date as published, when available."New value: +"The source's own designation date as YYYY-MM-DD; absent when unpublished."
    • addedOutput schema / properties / hits / items / properties / referenceNumber
      Added value: +{
      +  "description": "The list's published reference number (UN, EU, UK OFSI Group ID); absent when the list publishes none for the entry.",
      +  "type": "string"
      +}
  7. Changed3 schema fields changed
    • changedInput schema / properties / name / description
      Previous value: -"The name to screen (person, organization, vessel, or aircraft)."New value: +"The name to screen (person, organization, vessel, or aircraft), in any script. It must contain at least one letter or digit, and at most 64 words and 1024 characters."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `mirror_not_ready`: The sanctions mirror has never completed an initial sync. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `name_not_searchable`: The name contains no letter or digit, so nothing in it can be matched. `name_too_long`: The name is longer than 64 words or 1024 characters. `mirror_not_ready`: The sanctions mirror has never completed an initial sync. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "mirror_not_ready"
      -]New value: +[
      +  "name_not_searchable",
      +  "name_too_long",
      +  "mirror_not_ready"
      +]
  8. Changed6 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
      +  {
      +    "not": {
      +      "required": [
      +        "error"
      +      ]
      +    },
      +    "required": [
      +      "hits",
      +      "caveat",
      +      "normalizedQuery",
      +      "matchModeUsed",
      +      "totalCount",
      +      "totalAvailable",
      +      "totalAvailableBasis",
      +      "hasMore"
      +    ]
      +  },
      +  {
      +    "required": [
      +      "error"
      +    ]
      +  }
      +]
    • addedOutput schema / properties / error
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Present when the call failed. Absent on success.",
      +  "properties": {
      +    "code": {
      +      "description": "JSON-RPC error code for this failure.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "data": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "reason": {
      +          "description": "Machine-readable failure mode. Declared by this tool: `mirror_not_ready`: The sanctions mirror has never completed an initial sync. Other values are possible when a failure originates below the handler.",
      +          "examples": [
      +            "mirror_not_ready"
      +          ],
      +          "type": "string"
      +        },
      +        "recovery": {
      +          "additionalProperties": {},
      +          "description": "Actionable next step for the caller.",
      +          "properties": {
      +            "hint": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "hint"
      +          ],
      +          "type": "object"
      +        },
      +        "retryable": {
      +          "description": "Whether retrying may succeed.",
      +          "type": "boolean"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "message": {
      +      "description": "Human-readable description of what went wrong.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "code",
      +    "message"
      +  ],
      +  "type": "object"
      +}
    • removedOutput schema / required
      Removed value: -[
      -  "hits",
      -  "caveat",
      -  "normalizedQuery",
      -  "matchModeUsed",
      -  "totalCount",
      -  "totalAvailable",
      -  "totalAvailableBasis",
      -  "hasMore"
      -]
  9. Changed11 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum number of potential matches to return."New value: +"Maximum number of potential matches to return in one page."
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "description": "Zero-based index of the first potential match to return. Re-call with the returned nextOffset to page through every match when hasMore is true; an offset past the end returns an empty page, not an error.",
      +  "maximum": 9007199254740991,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedOutput schema / properties / hasMore
      Added value: +{
      +  "description": "True when potential matches remain beyond this page — re-call with nextOffset.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / hits / description
      Previous value: -"Scored potential matches, highest-confidence first."New value: +"Potential matches, ranked by match type, then score, then how much of the query each candidate explains."
    • addedOutput schema / properties / hits / items / properties / queryTokenCoverage
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "How much of the query this candidate explains, as a literal token count — a second real measurement, never folded into score. It is the tie-break applied after score, because one shared exact token pins several candidates at the same score. Absent for exact/strong hits.",
      +  "properties": {
      +    "covered": {
      +      "description": "Query tokens individually matched by one of this candidate's tokens at the applied score floor.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "total": {
      +      "description": "Total tokens in the normalized query.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    }
      +  },
      +  "required": [
      +    "covered",
      +    "total"
      +  ],
      +  "type": "object"
      +}
    • addedOutput schema / properties / nextOffset
      Added value: +{
      +  "description": "The offset to request next. Present only when hasMore is true.",
      +  "type": "number"
      +}
    • changedOutput schema / properties / notice / description
      Previous value: -"Guidance when no candidate matched — how to broaden, and what an empty result does NOT mean."New value: +"Guidance when no candidate matched — how to broaden, and what an empty result does NOT mean — or when the requested offset sits past the end of the result set."
    • addedOutput schema / properties / totalAvailable
      Added value: +{
      +  "description": "Potential matches available across all pages, before limit and offset were applied.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / totalAvailableBasis
      Added value: +{
      +  "description": "How to read totalAvailable: exact = the complete strict match set; lower_bound = a bounded scan produced it (every fuzzy pass, and any strict pass that hit the raw-row scan cap), so more may exist.",
      +  "enum": [
      +    "exact",
      +    "lower_bound"
      +  ],
      +  "type": "string"
      +}
    • changedOutput schema / properties / totalCount / description
      Previous value: -"Number of potential matches returned."New value: +"Number of potential matches returned in this page."
    • changedOutput schema / required
      Previous value: -[
      -  "hits",
      -  "caveat",
      -  "normalizedQuery",
      -  "matchModeUsed",
      -  "totalCount"
      -]New value: +[
      +  "hits",
      +  "caveat",
      +  "normalizedQuery",
      +  "matchModeUsed",
      +  "totalCount",
      +  "totalAvailable",
      +  "totalAvailableBasis",
      +  "hasMore"
      +]
  10. Changed1 schema field changed
    • changedInput schema / properties / minScore / description
      Previous value: -"Jaro-Winkler similarity floor for fuzzy hits (0–1). Applies to fuzzy mode only; defaults to the server's configured floor."New value: +"Score floor for fuzzy hits (0–1), applied uniformly to every fuzzy candidate regardless of how it was matched (Jaro-Winkler, token, or phonetic). No hit below this score is returned. Applies to fuzzy mode only; defaults to the server's configured floor."
  11. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations only say readOnly/idempotent/closed-world; the description goes much further by disclosing the dedup rule (one OFAC entry ID published on both lists counts as one hit), that strict mode still runs a fuzzy pass on lists strict found nothing on, that a non-Latin name triggers an extra UK/UN pass, and that empty never means cleared. This is behavioral context an agent cannot get from the annotations or output schema.

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?

The opening sentence is well front-loaded with purpose and sources, but the strict-mode sentence is a single sprawling clause chain that duplicates the matchMode schema text almost exactly, and the minScore mechanics are restated again. Substantial length is spent re-explaining structured fields rather than on the caveats that genuinely need prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, multi-list screening tool with an output schema, the definition covers the critical caveats—list loading gaps, scoring, paging, and the not-a-determination warning—so an agent can call it responsibly. The residual gap is routing between this and the identifier/entity siblings, which the description leaves to inference.

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 description's matchMode and minScore prose is close to a verbatim restatement of the schema's own enum/number descriptions, so little new meaning is added. The only incremental points are that results are paged via totalAvailable/hasMore/nextOffset and that limit is clamped, both already documented in 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?

"Screen a name (person, company, vessel, aircraft) against loaded sanctions and export-control watchlists" names a specific verb and resource and enumerates the source regimes (OFAC SDN/Consolidated, EU, UK, UN, BIS/State CSL). The scope is unmistakably name-based screening, which separates it from an identifier-screening sibling even without that sibling being named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit operational context: consult sanctions_list_sources before interpreting an empty result because zero-record CSL lists are not loaded, page with nextOffset when hasMore is true, and treat output as a review aid rather than a determination. It stops short of naming when to prefer sanctions_screen_identifier for passports/IMO numbers or sanctions_get_entity for drilling into a hit, so alternatives are implied rather than stated.

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.