NASA MCP Server

NASA Earthdata CMR search

nasa_cmr

Read-onlyIdempotent

Search NASA's Common Metadata Repository for Earth science datasets or granule files using spatial, temporal, platform, and identifier filters, with cursor pagination.

Instructions

Search NASA's Common Metadata Repository (CMR) for Earth science collections (datasets) or granules (files). Supports identifiers, temporal and spatial filters (bounding_box, point, polygon, line, circle), platform/instrument/project, facets and sorting. Returns a compact normalized envelope by default (response_mode raw for upstream metadata) and a next_cursor for Search After pagination: continue by passing only {"cursor": next_cursor}. Collection matches describe datasets; they do not prove granules exist for a given time or place. No API key needed.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`doi`	No	Collections only: DOI, e.g. 10.5067/GHGMR-4FJ04.
`bbox`	No	Compatibility alias for bounding_box (sent to CMR as bounding_box).
`line`	No	Line "lon1,lat1,lon2,lat2,...".
`page`	No	DEPRECATED page-number pagination (CMR page_num). Prefer cursor. Cannot be combined with cursor or offset.
`limit`	No	Records per page (1-100).
`point`	No	Point "lon,lat".
`circle`	No	Circle "lon,lat,radius" with radius in metres (10-6000000).
`cursor`	No	next_cursor from a previous response. Continue with the cursor alone; omitted filters are restored from it.
`fields`	No	Compact mode only: normalized fields to return. concept_id is always included. Defaults to all fields except summary.
`format`	No	Upstream CMR metadata format. json/umm_json support compact output; others are returned raw. dif, dif10, opendata: collections only; stac: granules only.	json
`offset`	No	DEPRECATED offset pagination. Prefer cursor. Cannot be combined with cursor or page.
`keyword`	No	Collections only: free-text keyword search.
`polygon`	No	Polygon "lon1,lat1,...,lon1,lat1": closed, counter-clockwise (CMR rejects clockwise rings).
`project`	No	Project/campaign short name(s).
`version`	No	Collection version.
`platform`	No	Platform short name(s), e.g. Terra.
`provider`	No	Provider ID(s), e.g. POCLOUD, LPCLOUD.
`sort_key`	No	Sort key(s), "-" prefix for descending. Collections: score, usage_score, entry_title, dataset_id, short_name, entry_id, start_date, end_date, platform, instrument, sensor, provider, revision_date, has_granules, create-data-date, ongoing. Granules: start_date, end_date, producer_granule_id, readable_granule_name, granule_ur, revision_date, cloud_cover, day_night_flag, data_size, provider, platform, instrument, sensor, online_only, browsable, entry_title, short_name, version, campaign, project.
`temporal`	No	Temporal range "start,end" in ISO 8601 (date or date-time, UTC assumed). Either side may be empty, e.g. "2020-01-01T00:00:00Z,".
`browsable`	No	Only records with (true) or without (false) browse imagery.
`concept_id`	No	Concept ID(s). For granule searches a collection concept ID (C...) also selects that collection, as in CMR.
`instrument`	No	Instrument short name(s), e.g. MODIS.
`short_name`	No	Collection short name(s).
`cloud_cover`	No	Granules only: cloud cover range "min,max" in percent.
`entry_title`	No	Collection entry title.
`online_only`	No	Only online (true) or offline (false) records.
`search_type`	No	Search collections (datasets) or granules (files).	collections
`bounding_box`	No	Bounding box west,south,east,north (lon/lat degrees). west > east crosses the antimeridian (supported by CMR).
`cloud_hosted`	No	Collections only: restrict to cloud-hosted (true) or not (false).
`downloadable`	No	Only records with (true) or without (false) downloadable data links.
`has_granules`	No	Collections only: require (true) or exclude (false) collections with granules.
`response_mode`	No	compact (default for json/umm_json): normalized records. raw: upstream metadata as returned (default for other formats).
`day_night_flag`	No	Granules only: DAY, NIGHT, BOTH or UNSPECIFIED.
`include_facets`	No	Include CMR v2 facets (counts by keyword, platform, ...).
`granule_data_format`	No	Collections only: granule data format(s), e.g. netCDF-4.
`processing_level_id`	No	Collections only: processing level(s), e.g. 3, L2.
`producer_granule_id`	No	Granules only: producer granule ID.
`collection_concept_id`	No	Granules only: collection concept ID(s) to search within.
`readable_granule_name`	No	Granules only: granule name (supports CMR * and ? wildcards).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`raw`	No
`error`	No
`facets`	No
`format`	Yes
`source`	Yes
`status`	Yes
`results`	Yes
`warnings`	Yes
`total_hits`	Yes
`next_cursor`	Yes
`search_type`	Yes
`retrieved_at`	Yes
`response_mode`	Yes
`returned_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed54 schema fields changedv1.2.0Oct 1, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / bbox

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "items": {
+        "type": "number"
+      },
+      "maxItems": 4,
+      "minItems": 4,
+      "type": "array"
+    }
+  ],
+  "description": "Compatibility alias for bounding_box (sent to CMR as bounding_box)."
+}

addedInput schema / properties / bounding_box

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "items": {
+        "type": "number"
+      },
+      "maxItems": 4,
+      "minItems": 4,
+      "type": "array"
+    }
+  ],
+  "description": "Bounding box west,south,east,north (lon/lat degrees). west > east crosses the antimeridian (supported by CMR)."
+}

addedInput schema / properties / browsable

Added value: +{
+  "description": "Only records with (true) or without (false) browse imagery.",
+  "type": "boolean"
+}

addedInput schema / properties / circle

Added value: +{
+  "description": "Circle \"lon,lat,radius\" with radius in metres (10-6000000).",
+  "type": "string"
+}

addedInput schema / properties / cloud_cover

Added value: +{
+  "description": "Granules only: cloud cover range \"min,max\" in percent.",
+  "pattern": "^(\\d+(\\.\\d+)?)?,(\\d+(\\.\\d+)?)?$",
+  "type": "string"
+}

addedInput schema / properties / cloud_hosted

Added value: +{
+  "description": "Collections only: restrict to cloud-hosted (true) or not (false).",
+  "type": "boolean"
+}

addedInput schema / properties / collection_concept_id

Added value: +{
+  "anyOf": [
+    {
+      "pattern": "^[A-Z]{1,4}\\d+-[A-Za-z0-9_]+$",
+      "type": "string"
+    },
+    {
+      "items": {
+        "pattern": "^[A-Z]{1,4}\\d+-[A-Za-z0-9_]+$",
+        "type": "string"
+      },
+      "maxItems": 100,
+      "minItems": 1,
+      "type": "array"
+    }
+  ],
+  "description": "Granules only: collection concept ID(s) to search within."
+}

addedInput schema / properties / concept_id

Added value: +{
+  "anyOf": [
+    {
+      "pattern": "^[A-Z]{1,4}\\d+-[A-Za-z0-9_]+$",
+      "type": "string"
+    },
+    {
+      "items": {
+        "pattern": "^[A-Z]{1,4}\\d+-[A-Za-z0-9_]+$",
+        "type": "string"
+      },
+      "maxItems": 100,
+      "minItems": 1,
+      "type": "array"
+    }
+  ],
+  "description": "Concept ID(s). For granule searches a collection concept ID (C...) also selects that collection, as in CMR."
+}

addedInput schema / properties / cursor

Added value: +{
+  "description": "next_cursor from a previous response. Continue with the cursor alone; omitted filters are restored from it.",
+  "maxLength": 8192,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / day_night_flag

Added value: +{
+  "description": "Granules only: DAY, NIGHT, BOTH or UNSPECIFIED.",
+  "enum": [
+    "DAY",
+    "NIGHT",
+    "BOTH",
+    "UNSPECIFIED"
+  ],
+  "type": "string"
+}

addedInput schema / properties / doi

Added value: +{
+  "description": "Collections only: DOI, e.g. 10.5067/GHGMR-4FJ04.",
+  "maxLength": 200,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / downloadable

Added value: +{
+  "description": "Only records with (true) or without (false) downloadable data links.",
+  "type": "boolean"
+}

addedInput schema / properties / entry_title

Added value: +{
+  "description": "Collection entry title.",
+  "maxLength": 1000,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / fields

Added value: +{
+  "description": "Compact mode only: normalized fields to return. concept_id is always included. Defaults to all fields except summary.",
+  "items": {
+    "enum": [
+      "concept_id",
+      "title",
+      "short_name",
+      "version",
+      "provider",
+      "time_start",
+      "time_end",
+      "platforms",
+      "instruments",
+      "processing_level",
+      "doi",
+      "cloud_hosted",
+      "online_access",
+      "links",
+      "summary",
+      "collection_concept_id",
+      "producer_granule_id",
+      "day_night_flag",
+      "cloud_cover",
+      "browse_available"
+    ],
+    "type": "string"
+  },
+  "maxItems": 20,
+  "minItems": 1,
+  "type": "array"
+}

changedInput schema / properties / format / description

Previous value: -"Response format"New value: +"Upstream CMR metadata format. json/umm_json support compact output; others are returned raw. dif, dif10, opendata: collections only; stac: granules only."

changedInput schema / properties / format / enum

Previous value: -[
-  "json",
-  "umm_json",
-  "atom",
-  "echo10",
-  "iso19115",
-  "iso_smap",
-  "kml"
-]New value: +[
+  "json",
+  "umm_json",
+  "atom",
+  "echo10",
+  "iso19115",
+  "kml",
+  "csv",
+  "xml",
+  "native",
+  "dif",
+  "dif10",
+  "opendata",
+  "stac"
+]

addedInput schema / properties / granule_data_format

Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 256,
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "items": {
+        "maxLength": 256,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 20,
+      "minItems": 1,
+      "type": "array"
+    }
+  ],
+  "description": "Collections only: granule data format(s), e.g. netCDF-4."
+}

addedInput schema / properties / has_granules

Added value: +{
+  "description": "Collections only: require (true) or exclude (false) collections with granules.",
+  "type": "boolean"
+}

addedInput schema / properties / include_facets

Added value: +{
+  "description": "Include CMR v2 facets (counts by keyword, platform, ...).",
+  "type": "boolean"
+}

addedInput schema / properties / instrument

Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 256,
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "items": {
+        "maxLength": 256,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 20,
+      "minItems": 1,
+      "type": "array"
+    }
+  ],
+  "description": "Instrument short name(s), e.g. MODIS."
+}

changedInput schema / properties / keyword / description

Previous value: -"Search keyword"New value: +"Collections only: free-text keyword search."

addedInput schema / properties / keyword / maxLength
```
Added value: +1000
```
addedInput schema / properties / keyword / minLength
```
Added value: +1
```
addedInput schema / properties / limit / default
```
Added value: +10
```

changedInput schema / properties / limit / description

Previous value: -"Maximum number of results to return"New value: +"Records per page (1-100)."

addedInput schema / properties / limit / maximum
```
Added value: +100
```
addedInput schema / properties / limit / minimum
```
Added value: +1
```

changedInput schema / properties / limit / type

Previous value: -"number"New value: +"integer"

addedInput schema / properties / line

Added value: +{
+  "description": "Line \"lon1,lat1,lon2,lat2,...\".",
+  "maxLength": 8000,
+  "type": "string"
+}

addedInput schema / properties / offset

Added value: +{
+  "description": "DEPRECATED offset pagination. Prefer cursor. Cannot be combined with cursor or page.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / online_only

Added value: +{
+  "description": "Only online (true) or offline (false) records.",
+  "type": "boolean"
+}

changedInput schema / properties / page / description

Previous value: -"Page number for pagination"New value: +"DEPRECATED page-number pagination (CMR page_num). Prefer cursor. Cannot be combined with cursor or offset."

addedInput schema / properties / page / maximum
```
Added value: +9007199254740991
```
addedInput schema / properties / page / minimum
```
Added value: +1
```

changedInput schema / properties / page / type

Previous value: -"number"New value: +"integer"

addedInput schema / properties / platform

Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 256,
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "items": {
+        "maxLength": 256,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 20,
+      "minItems": 1,
+      "type": "array"
+    }
+  ],
+  "description": "Platform short name(s), e.g. Terra."
+}

addedInput schema / properties / point

Added value: +{
+  "description": "Point \"lon,lat\".",
+  "maxLength": 8000,
+  "type": "string"
+}

addedInput schema / properties / polygon

Added value: +{
+  "description": "Polygon \"lon1,lat1,...,lon1,lat1\": closed, counter-clockwise (CMR rejects clockwise rings).",
+  "maxLength": 8000,
+  "type": "string"
+}

addedInput schema / properties / processing_level_id

Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 40,
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "items": {
+        "maxLength": 40,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 20,
+      "minItems": 1,
+      "type": "array"
+    }
+  ],
+  "description": "Collections only: processing level(s), e.g. 3, L2."
+}

addedInput schema / properties / producer_granule_id

Added value: +{
+  "description": "Granules only: producer granule ID.",
+  "maxLength": 1000,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / project

Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 256,
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "items": {
+        "maxLength": 256,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 20,
+      "minItems": 1,
+      "type": "array"
+    }
+  ],
+  "description": "Project/campaign short name(s)."
+}

addedInput schema / properties / provider

Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 80,
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "items": {
+        "maxLength": 80,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 20,
+      "minItems": 1,
+      "type": "array"
+    }
+  ],
+  "description": "Provider ID(s), e.g. POCLOUD, LPCLOUD."
+}

addedInput schema / properties / readable_granule_name

Added value: +{
+  "description": "Granules only: granule name (supports CMR * and ? wildcards).",
+  "maxLength": 1000,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / response_mode

Added value: +{
+  "description": "compact (default for json/umm_json): normalized records. raw: upstream metadata as returned (default for other formats).",
+  "enum": [
+    "compact",
+    "raw"
+  ],
+  "type": "string"
+}

changedInput schema / properties / search_type / description

Previous value: -"Search type (collections or granules)"New value: +"Search collections (datasets) or granules (files)."

addedInput schema / properties / short_name

Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 256,
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "items": {
+        "maxLength": 256,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 20,
+      "minItems": 1,
+      "type": "array"
+    }
+  ],
+  "description": "Collection short name(s)."
+}

addedInput schema / properties / sort_key / anyOf

Added value: +[
+  {
+    "pattern": "^[+-]?[a-z_-]+$",
+    "type": "string"
+  },
+  {
+    "items": {
+      "pattern": "^[+-]?[a-z_-]+$",
+      "type": "string"
+    },
+    "maxItems": 3,
+    "minItems": 1,
+    "type": "array"
+  }
+]

changedInput schema / properties / sort_key / description

Previous value: -"Field to sort results by"New value: +"Sort key(s), \"-\" prefix for descending. Collections: score, usage_score, entry_title, dataset_id, short_name, entry_id, start_date, end_date, platform, instrument, sensor, provider, revision_date, has_granules, create-data-date, ongoing. Granules: start_date, end_date, producer_granule_id, readable_granule_name, granule_ur, revision_date, cloud_cover, day_night_flag, data_size, provider, platform, instrument, sensor, online_only, browsable, entry_title, short_name, version, campaign, project."

removedInput schema / properties / sort_key / type
```
Removed value: -"string"
```

addedInput schema / properties / temporal

Added value: +{
+  "description": "Temporal range \"start,end\" in ISO 8601 (date or date-time, UTC assumed). Either side may be empty, e.g. \"2020-01-01T00:00:00Z,\".",
+  "type": "string"
+}

addedInput schema / properties / version

Added value: +{
+  "description": "Collection version.",
+  "maxLength": 80,
+  "minLength": 1,
+  "type": "string"
+}

removedInput schema / required

Removed value: -[
-  "keyword",
-  "search_type",
-  "format"
-]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "error": {
+      "additionalProperties": false,
+      "properties": {
+        "http_status": {
+          "anyOf": [
+            {
+              "maximum": 9007199254740991,
+              "minimum": -9007199254740991,
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "kind": {
+          "type": "string"
+        },
+        "message": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "kind",
+        "message",
+        "http_status"
+      ],
+      "type": "object"
+    },
+    "facets": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "name": {
+            "type": "string"
+          },
+          "values": {
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "count": {
+                  "type": [
+                    "number",
+                    "null"
+                  ]
+                },
+                "title": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "title",
+                "count"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          }
+        },
+        "required": [
+          "name",
+          "values"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "format": {
+      "enum": [
+        "json",
+        "umm_json",
+        "atom",
+        "echo10",
+        "iso19115",
+        "kml",
+        "csv",
+        "xml",
+        "native",
+        "dif",
+        "dif10",
+        "opendata",
+        "stac"
+      ],
+      "type": "string"
+    },
+    "next_cursor": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "raw": {},
+    "response_mode": {
+      "enum": [
+        "compact",
+        "raw"
+      ],
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "browse_available": {
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "cloud_cover": {
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "cloud_hosted": {
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "collection_concept_id": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "concept_id": {
+            "type": "string"
+          },
+          "day_night_flag": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "doi": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "instruments": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "links": {
+            "anyOf": [
+              {
+                "items": {
+                  "additionalProperties": false,
+                  "properties": {
+                    "title": {
+                      "type": [
+                        "string",
+                        "null"
+                      ]
+                    },
+                    "type": {
+                      "type": [
+                        "string",
+                        "null"
+                      ]
+                    },
+                    "url": {
+                      "type": "string"
+                    }
+                  },
+                  "required": [
+                    "url",
+                    "type",
+                    "title"
+                  ],
+                  "type": "object"
+                },
+                "type": "array"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "online_access": {
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "platforms": {
+            "anyOf": [
+              {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "processing_level": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "producer_granule_id": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "provider": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "short_name": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "summary": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "time_end": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "time_start": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "version": {
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "concept_id"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "retrieved_at": {
+      "type": "string"
+    },
+    "returned_count": {
+      "anyOf": [
+        {
+          "maximum": 9007199254740991,
+          "minimum": -9007199254740991,
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "search_type": {
+      "enum": [
+        "collections",
+        "granules"
+      ],
+      "type": "string"
+    },
+    "source": {
+      "additionalProperties": false,
+      "properties": {
+        "request_id": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "retrieved_at": {
+          "type": "string"
+        },
+        "service": {
+          "type": "string"
+        },
+        "took_ms": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "url": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "service",
+        "url",
+        "request_id",
+        "took_ms",
+        "retrieved_at"
+      ],
+      "type": "object"
+    },
+    "status": {
+      "enum": [
+        "success",
+        "no_results",
+        "error"
+      ],
+      "type": "string"
+    },
+    "total_hits": {
+      "anyOf": [
+        {
+          "maximum": 9007199254740991,
+          "minimum": -9007199254740991,
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "warnings": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "status",
+    "search_type",
+    "format",
+    "response_mode",
+    "results",
+    "returned_count",
+    "total_hits",
+    "next_cursor",
+    "source",
+    "retrieved_at",
+    "warnings"
+  ],
+  "type": "object"
+}

Changed3 schema fields changedv1.0.0Jan 2, 2026

addedInput schema / properties / format

Added value: +{
+  "default": "json",
+  "description": "Response format",
+  "enum": [
+    "json",
+    "umm_json",
+    "atom",
+    "echo10",
+    "iso19115",
+    "iso_smap",
+    "kml"
+  ],
+  "type": "string"
+}

addedInput schema / properties / search_type

Added value: +{
+  "default": "collections",
+  "description": "Search type (collections or granules)",
+  "enum": [
+    "collections",
+    "granules"
+  ],
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "keyword"
-]New value: +[
+  "keyword",
+  "search_type",
+  "format"
+]

First observedAug 18, 2025

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: compact envelope is the default with raw for upstream metadata, cursor-based Search After pagination semantics, and 'No API key needed' (auth requirement).

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

Conciseness4/5

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

Purpose is front-loaded in the first sentence and each subsequent sentence carries distinct payload (filters, response mode, pagination, caveat, auth). It is dense but every clause earns its place; only the filter enumeration is slightly list-like.

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

Completeness5/5

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

An output schema exists so return values need not be explained, yet the description still clarifies the compact-vs-raw envelope and the next_cursor contract. Combined with the auth note and the granules caveat, an agent has everything needed to call it correctly.

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 description coverage is 100%, so the 39 parameters are fully documented structurally; baseline 3 applies. The description usefully groups the filter families (identifiers, temporal/spatial, platform/instrument/project, facets, sorting) and flags the compact/raw response_mode behavior, but adds no syntax beyond 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 (Search) plus the exact resource (NASA's Common Metadata Repository) and the two search domains (collections/datasets vs granules/files). Among siblings it is the only CMR metadata-search tool, so an agent can place it immediately.

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 practical usage direction: continue pagination by passing only {"cursor": next_cursor}, and warns that collection matches do not prove granules exist for a time/place. It does not name explicit when-not-to-use scenarios, but no sibling tool overlaps enough to require exclusion guidance, so 4 is fair.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.