{
  "format_version": "1",
  "case": "soil-metadata",
  "title": "Soil sample field check",
  "question": "Which returned NMDC soil samples have a collection date, coordinates and depth in metres?",
  "mode": "recorded",
  "simulation": false,
  "registry_revision": "2026-11-09",
  "generated_at": null,
  "replay_clock": "2026-11-09T00:00:00Z",
  "timestamp_note": "Envelope retrieval timestamps use a fixed replay clock, not publisher retrieval times. Actual fixture capture times appear in the manifest; null means unrecorded.",
  "fixtures": [
    {
      "file": "nmdc-runtime.json",
      "sha256": "a47cb8d2a0a93dcec1b30c3de2eca0769c8e5fb4fe9eca8edda61eb580432b78",
      "captured_at": "2026-10-08T23:37:56.653277+00:00"
    }
  ],
  "limitations": [
    "The place filter matches text containing Washington; it does not test state boundaries.",
    "Counts describe this page only. Depth counts as present if the response gives a value or a range bound in metres."
  ],
  "steps": [
    {
      "tool": "bio.search_biosamples",
      "args": {
        "ecosystem_type": "Soil",
        "place": "washington",
        "rows": 5
      },
      "envelope": {
        "data": {
          "biosamples": [
            {
              "sample_id": "nmdc:bsm-13-mrzb2q96",
              "name": "Groundwater microbial communities from the Columbia River, Washington, USA - GW-RW N1_20_30",
              "studies": [
                "nmdc:sty-11-aygzgv51"
              ],
              "collected": "2014-04-01",
              "latitude": 46.372,
              "longitude": -119.272,
              "place": "USA: Columbia River, Washington",
              "ecosystem": [
                "Environmental",
                "Terrestrial",
                "Soil",
                "Sand"
              ],
              "env_broad_scale": "ENVO:00000873",
              "env_local_scale": "ENVO:00000022",
              "env_medium": "ENVO:01000017",
              "depth_m": null
            },
            {
              "sample_id": "nmdc:bsm-13-4aw9ra87",
              "name": "Groundwater microbial communities from the Columbia River, Washington, USA - GW-RW N1_30_40",
              "studies": [
                "nmdc:sty-11-aygzgv51"
              ],
              "collected": "2014-04-01",
              "latitude": 46.372,
              "longitude": -119.272,
              "place": "USA: Columbia River, Washington",
              "ecosystem": [
                "Environmental",
                "Terrestrial",
                "Soil",
                "Sand"
              ],
              "env_broad_scale": "ENVO:00000873",
              "env_local_scale": "ENVO:00000022",
              "env_medium": "ENVO:01000017",
              "depth_m": null
            },
            {
              "sample_id": "nmdc:bsm-13-z9wten89",
              "name": "Groundwater microbial communities from the Columbia River, Washington, USA - GW-RW N1_00_10",
              "studies": [
                "nmdc:sty-11-aygzgv51"
              ],
              "collected": "2014-04-01",
              "latitude": 46.372,
              "longitude": -119.272,
              "place": "USA: Columbia River, Washington",
              "ecosystem": [
                "Environmental",
                "Terrestrial",
                "Soil",
                "Sand"
              ],
              "env_broad_scale": "ENVO:00000873",
              "env_local_scale": "ENVO:00000022",
              "env_medium": "ENVO:01000017",
              "depth_m": null
            },
            {
              "sample_id": "nmdc:bsm-13-wktc3357",
              "name": "Groundwater microbial communities from the Columbia River, Washington, USA - GW-RW N1_40_50",
              "studies": [
                "nmdc:sty-11-aygzgv51"
              ],
              "collected": "2014-04-01",
              "latitude": 46.372,
              "longitude": -119.272,
              "place": "USA: Columbia River, Washington",
              "ecosystem": [
                "Environmental",
                "Terrestrial",
                "Soil",
                "Sand"
              ],
              "env_broad_scale": "ENVO:00000873",
              "env_local_scale": "ENVO:00000022",
              "env_medium": "ENVO:01000017",
              "depth_m": null
            },
            {
              "sample_id": "nmdc:bsm-13-ap544f22",
              "name": "Groundwater microbial communities from the Columbia River, Washington, USA - GW-RW N2_00_30",
              "studies": [
                "nmdc:sty-11-aygzgv51"
              ],
              "collected": "2014-04-01",
              "latitude": 46.372,
              "longitude": -119.272,
              "place": "USA: Columbia River, Washington",
              "ecosystem": [
                "Environmental",
                "Terrestrial",
                "Soil",
                "Sand"
              ],
              "env_broad_scale": "ENVO:00000873",
              "env_local_scale": "ENVO:00000022",
              "env_medium": "ENVO:01000017",
              "depth_m": null
            }
          ],
          "record_count": 5,
          "total_matches": 188,
          "page": 1,
          "filter_applied": {
            "ecosystem_type": {
              "$regex": "(?i)^Soil$"
            },
            "geo_loc_name.has_raw_value": {
              "$regex": "(?i)washington"
            }
          },
          "note": "Sample metadata as submitted. ecosystem_type matches NMDC's whole value without regard to case ('soil', 'Freshwater'); env_medium and place match a substring without regard to case; collected matches the start of the date as written ('2017', '2017-06'). Depth is reported only where it was stated in metres. Metadata only. Reads, assemblies and annotations are held at JGI, EMSL and the sequence archives; a study's DOIs in access_recipes lead to them and are never fetched here."
        },
        "provenance": [
          {
            "id": "source_01",
            "source_id": "nmdc-runtime",
            "steward": "Lawrence Berkeley National Laboratory",
            "funder": "Office of Science",
            "system": "National Microbiome Data Collaborative Runtime API",
            "dataset": "National Microbiome Data Collaborative Runtime API",
            "dataset_version": "current",
            "authority_level": "official_secondary",
            "access_path": "live",
            "source_updated_at": null,
            "retrieved_at": "2026-11-09T00:00:00Z",
            "cache_age_seconds": 0
          }
        ],
        "evidence": [
          {
            "id": "evidence_01",
            "source_ref": "source_01",
            "record_id": "nmdc:bsm-13-mrzb2q96",
            "locator": null,
            "retrieved_at": "2026-11-09T00:00:00Z",
            "effective_at": "2014-04-01",
            "transformations": [
              "normalize"
            ],
            "payload_hash": null,
            "raw_recovery": "available"
          },
          {
            "id": "evidence_02",
            "source_ref": "source_01",
            "record_id": "nmdc:bsm-13-4aw9ra87",
            "locator": null,
            "retrieved_at": "2026-11-09T00:00:00Z",
            "effective_at": "2014-04-01",
            "transformations": [
              "normalize"
            ],
            "payload_hash": null,
            "raw_recovery": "available"
          },
          {
            "id": "evidence_03",
            "source_ref": "source_01",
            "record_id": "nmdc:bsm-13-z9wten89",
            "locator": null,
            "retrieved_at": "2026-11-09T00:00:00Z",
            "effective_at": "2014-04-01",
            "transformations": [
              "normalize"
            ],
            "payload_hash": null,
            "raw_recovery": "available"
          },
          {
            "id": "evidence_04",
            "source_ref": "source_01",
            "record_id": "nmdc:bsm-13-wktc3357",
            "locator": null,
            "retrieved_at": "2026-11-09T00:00:00Z",
            "effective_at": "2014-04-01",
            "transformations": [
              "normalize"
            ],
            "payload_hash": null,
            "raw_recovery": "available"
          },
          {
            "id": "evidence_05",
            "source_ref": "source_01",
            "record_id": "nmdc:bsm-13-ap544f22",
            "locator": null,
            "retrieved_at": "2026-11-09T00:00:00Z",
            "effective_at": "2014-04-01",
            "transformations": [
              "normalize"
            ],
            "payload_hash": null,
            "raw_recovery": "available"
          }
        ],
        "coverage": {
          "registry": "covered",
          "execution": "complete",
          "pagination": "truncated",
          "source_claim": "complete",
          "result": "hit",
          "sources_searched": [
            "nmdc-runtime"
          ],
          "known_limitations": [
            "Metadata, not sequence data. Reads, assemblies and annotations live in the sequence archives and at JGI, and are reached through a study's DOIs rather than through this source.",
            "Only 8 of 85 studies carry an ecosystem classification of their own; the rest are classified sample by sample. An ecosystem filter on studies therefore misses most of them, and the biosample filter is the one to use.",
            "Place is free text as submitted ('USA: Washington, Abby Road'), so a place search is a substring match and a state name may miss samples recorded only by site or coordinates.",
            "Studies NMDC has ingested, not every microbiome study. Most of the 85 are JGI or EMSL projects and a consortium study such as NEON's appears once with thousands of samples, so counts describe NMDC's holdings rather than the field."
          ]
        },
        "warnings": [
          {
            "code": "terms_note",
            "message": "No published rate limit and no data-use statement on the API itself; the data portal's usage terms were not found in a scripted read.",
            "source_id": "nmdc-runtime"
          }
        ],
        "_execution": {
          "server": "doe-mcp",
          "server_version": "0.1.0.dev0",
          "tool": "bio.search_biosamples",
          "tool_contract_version": "1",
          "envelope_version": "1",
          "adapters": {
            "osti_family": "1",
            "opendatasoft": "1",
            "json_document": "1",
            "curated": "1",
            "eia_v2": "1",
            "fueleconomy": "1",
            "text_feed": "1",
            "postgrest": "1",
            "federal_register": "1",
            "vips": "1",
            "daymet": "1",
            "essdive": "1",
            "esgf": "1",
            "sage": "1",
            "optimade": "1",
            "basis_sets": "1",
            "facility_status": "1",
            "gcam_csv": "1",
            "nmdc": "1",
            "none": "1",
            "self_registry": "1"
          },
          "registry_revision": "2026-11-09",
          "request_id": "recorded-workflow"
        }
      }
    }
  ],
  "worksheet": {
    "caption": "Soil sample field check",
    "columns": [
      "Sample ID",
      "Place",
      "Collected",
      "Latitude",
      "Longitude",
      "Depth (m)",
      "Minimum depth (m)",
      "Maximum depth (m)",
      "Step 1 evidence ID"
    ],
    "rows": [
      [
        "nmdc:bsm-13-mrzb2q96",
        "USA: Columbia River, Washington",
        "2014-04-01",
        46.372,
        -119.272,
        null,
        null,
        null,
        "evidence_01"
      ],
      [
        "nmdc:bsm-13-4aw9ra87",
        "USA: Columbia River, Washington",
        "2014-04-01",
        46.372,
        -119.272,
        null,
        null,
        null,
        "evidence_02"
      ],
      [
        "nmdc:bsm-13-z9wten89",
        "USA: Columbia River, Washington",
        "2014-04-01",
        46.372,
        -119.272,
        null,
        null,
        null,
        "evidence_03"
      ],
      [
        "nmdc:bsm-13-wktc3357",
        "USA: Columbia River, Washington",
        "2014-04-01",
        46.372,
        -119.272,
        null,
        null,
        null,
        "evidence_04"
      ],
      [
        "nmdc:bsm-13-ap544f22",
        "USA: Columbia River, Washington",
        "2014-04-01",
        46.372,
        -119.272,
        null,
        null,
        null,
        "evidence_05"
      ]
    ],
    "missing": {
      "collection date": 0,
      "coordinate pair": 0,
      "depth in metres": 5
    }
  }
}