# find_data_sources Find Data Sources · v1.0.0 · curated Search the Vlada substrate catalog by keyword. Returns the matching data sources (commercial TiC, hospital HPT, Medicare, drug pricing, provider identity, curated marts, provenance registries) ranked by relevance. Compact by default (identity + queryable + claim ceiling + the exact describe_data_source call per hit); pass verbosity='full' for the previous full source_product_card per result. Paginates with limit (default 25, max 200) + offset; the response carries total_count, returned_count, and offset. Optional filters: {domain, stage, status, limit}. Agents call this first to discover what data Vlada has. Since 2026-09-02 the answer leads with DATA POINTS (`data_points`: the measure/dimension asked for, with its source, door, table.column and must-read trap) and the table cards follow as physical locations. Every hit carries `source_code` -- the one public code, which describe_data_source accepts verbatim -- alongside the table's `source_fqn`. Points and tables are ranked by ONE ranker (the authored data-point scorer). Retired tables are never returned; they appear only as `supersedes` on the live successor's card. BOUNDED (2026-09-18): the default call is compact and paged -- both the table cards and the data points come back a page at a time, each with its own total and next offset -- so a default call can never truncate. Pass verbosity='full' for the whole point record and the full source_product_card per hit. **Inputs.** - `query`: - `filters`: - `world`: - `max_points`: - `limit`: - `offset`: - `verbosity`: **A real answer** (customer seat, 0.65 s, args `{"query":"medicare physician fee schedule","limit":5}`): ```json { "value": { "query": "medicare physician fee schedule", "filters": null, "verbosity": "compact", "status": "matched", "retrieval_mode": "lexical", "scope_verification": { "status": "not_verified", "basis": "catalog_match_only", "geography": "not_verified", "time_coverage": "not_verified", "population": "not_verified", "completeness": "not_verified" }, "ranker": "authored_data_point_scorer", "excludes": "retired", "data_points": [ { "rank": 1, "world": "w2", "data_point": { "id": "w2.puf.physician_avg_medicare_allowed", "name": "Medicare average allowed amount by provider and service", "unit": "USD_per_service", "kind": "measure" }, "source": { "id": "cms_puf_physician_other_practitioners", "source_code": "cms_puf_physician_other_practitioners", "title": "Medicare Physician & Other Practitioners public use files (by provider and service; by geography and service)", "how_to_reach_it": "sql" }, "location": { "table": "medicare_silver.fact_physician_by_provider_service", "column": "avg_medicare_allowed", "variants": [ "paid=avg_medicare_payment", "standardized=avg_medicare_standardized", "submitted=avg_submitted_charge", "services=tot_services", "beneficiaries=tot_benes" ], "required_filters": [ "is_current=true" ] }, "trap": { "must_read": "Always filter data_year and a state or code; averages of paid claims; null is suppressed.", "ids": [ "data_year_pin", "claims_average_not_fee_schedule", "small_cell_suppressed_null", "heavy_scan" ] }, "next": "bounded query_substrate on medicare_silver.fact_physician_by_provider_service", "fetch": "describe_data_source(source_fqn='cms_puf_physician_other_practitioners')", "relevance": 51 }, { "rank": 2, "world": "w2", "data_point": { "id": "w2.pfs.national_allowed_amount", "name": "PFS national allowed amount", "unit": "USD", "kind": "rate" }, "source": { "id": "cms_pfs_relative_value_files", "source_code": "cms_pfs_relative_value_files", "title": "Physician Fee Schedule relative value files (RVUs, indicators, conversion factor, GPCI, locality configuration)", "how_to_reach_it": "sql" }, "location": { "table": "medicare_silver.fact_pfs_rvu", "column": "conversion_factor", "variants": [ "total_nonfacility_rvu=total_non_facility_rvu", "total_facility_rvu=total_facility_rvu", "status=status_code" ], "required_filters": [] }, "trap": { "must_read": "Compute RVU x conversion factor after filtering implausible rows; status_code says whether the code is payable; national only.", "ids": [ "year_pin", "implausible_conversion_factor_rows", "locality_not_on_rvu" ] }, "next": "call medicare_allowed", "fetch": "describe_data_source(source_fqn='cms_pfs_relative_value_files')", "relevance": 45 }, { "rank": 3, "world": "w2", "data_point": { "id": "w2.clfs.national_limit_amount", "name": "CLFS national limitation amount", "unit": "USD", "kind": "rate" }, "source": { "id": "cms_clfs_national_rates", "source_code": "cms_clfs_national_rates", "title": "Clinical Laboratory Fee Schedule (national limitation amounts)", "how_to_reach_it": "sql" }, "location": { "table": "medicare_silver.fact_clfs_national_rate", "column": "national_limit_amount", "variants": [], "required_filters": [] }, "trap": { "must_read": "Pin calendar_year and quarter; do not union with the legacy locality table.", "ids": [ "quarter_pin" ] }, "next": "bounded query_substrate on medicare_silver.fact_clfs_national_rate", "fetch": "describe_data_source(source_fqn='cms_clfs_national_rates')", "relevance": 42 } ], "data_points_total_count": 3, "data_points_returned_count": 3, "data_points_detail_hint": "verbosity='full' returns grain, time pin, nulls, variants and basis for each point; describe_data_source(source_code) returns the table to query and a verified example.", "match_count": 322, "returned": 5, "total_count": 322, "returned_count": 5, "offset": 0, "limit": 5, "results": [ { "source_id": "cms_physician_by_provider_service", "source_code": "cms_puf_physician_other_practitioners", "title": "Medicare Physician & Other Practitioners \u2014 by Provider and Service (granular price)", "published_source_code": "cms_puf_physician_other_practitioners", "how_to_reach_it": "sql", "domain": "medicare", "status": "live", "grain": "One row per (data_year, rendering NPI, HCPCS, place of service) \u2014 charge/allowed/paid.", "queryable": true, "not_queryable_reason": null, "claim_ceiling": "queryable", "fetch": "describe_data_source(source_fqn='medicare_silver.fact_physician_by_provider_service')", "fetch_unavailable_reason": null, "relevance": 1051, "relevance_basis": "data_point", "relevance_why": "holds data point w2.puf.physician_avg_medicare_allowed", "world": "Medicare", "view": "By doctor" }, { "source_id": "medicare_physician_payment_by_geo", "source_code": "cms_puf_physician_other_practitioners", "title": "Medicare Physician & Other Practitioners by Geography (avg allowed/payment per HCPCS)", "published_source_code": "cms_puf_physician_other_practitioners", "how_to_reach_it": "sql", "domain": "medicare", "status": "live", "grain": "One row per (geography [National|State], HCPCS, place-of-service) per data year.", "queryable": true, "not_queryable_reason": null, "claim_ceiling": "queryable", "fetch": "describe_data_source(source_fqn='medicare_silver.fact_physician_payment_by_geo')", "fetch_unavailable_reason": ... (truncated) ``` REST: `POST https://api.vladahealth.com/v1/tools/find_data_sources` with the inputs as the JSON body. MCP: the tool by name.