Skip to main content
Glama
Sign In
opendata-atlas

opendata-atlas

by briandconnelly
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Search datasets

atlas_search_datasets
Read-only

Search a public open-data portal's datasets by topic or keyword to identify dataset candidates when you lack an ID; results include match evidence and queryability.

Instructions

Find a portal's datasets by topic. Call when you lack a dataset id.

Results are candidates: match_evidence lists the query words each one's metadata lacks. Only queryability "supported" can be described or queried; a tabular search also returns up to 3 external_matches, which cannot. Illustrative example: {"portal": "example-city", "query": "fire 911"}. Typically 1-3 s.

Input Schema

NameRequiredDescriptionDefault
queryNoWords to match; omit to list the most-viewed.
cursorNonext_cursor from the previous page; omit for page one.
detailNosummary (default) or full: adds descriptions.
portalYesPortal id (its hostname) or alias, from atlas_find_portals. Repeat it on every page of a paged call.
categoryNoExact category name, as in a result's category, e.g. Public Safety; omit for all.
page_sizeNoDefault 10.
asset_scopeNotabular (default): queryable datasets and filter views. all: adds federated ArcGIS and external links, which cannot be queried.

Output Schema

NameRequiredDescriptionDefault
sourceYes
datasetsYes
has_moreYes
truncatedNo
suggestionNo
next_cursorNo
match_evidenceNo
truncation_hintNo
external_matchesNo
external_search_statusNo
foreign_results_droppedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed18 schema fields changedv0.3.0
    • changedInput schema / properties / category / description
      Previous value: -"Exact category name, e.g. Public Safety; omit for all."New value: +"Exact category name, as in a result's category, e.g. Public Safety; omit for all."
    • addedOutput schema / $defs
      Added value: +{
+  "DatasetSummary": {
+    "additionalProperties": false,
+    "properties": {
+      "asset_type": {
+        "type": "string"
+      },
+      "category": {
+        "type": "string"
+      },
+      "dataset_id": {
+        "type": "string"
+      },
+      "derived_from": {
+        "type": "string"
+      },
+      "description": {
+        "type": "string"
+      },
+      "external_url": {
+        "type": "string"
+      },
+      "guide_uri": {
+        "type": "string"
+      },
+      "portal_url": {
+        "type": "string"
+      },
+      "queryability": {
+        "enum": [
+          "supported",
+          "external",
+          "unsupported",
+          "unknown"
+        ]
+      },
+      "title": {
+        "type": "string"
+      },
+      "updated_at": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "dataset_id",
+      "title",
+      "asset_type",
+      "queryability",
+      "portal_url"
+    ],
+    "type": "object"
+  }
+}
    • addedOutput schema / properties / datasets / items / $ref
      Added value: +"#/$defs/DatasetSummary"
    • removedOutput schema / properties / datasets / items / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / datasets / items / properties
      Removed value: -{
-  "asset_type": {
-    "type": "string"
-  },
-  "category": {
-    "type": "string"
-  },
-  "dataset_id": {
-    "type": "string"
-  },
-  "derived_from": {
-    "type": "string"
-  },
-  "description": {
-    "type": "string"
-  },
-  "external_url": {
-    "type": "string"
-  },
-  "guide_uri": {
-    "type": "string"
-  },
-  "portal_url": {
-    "type": "string"
-  },
-  "queryability": {
-    "enum": [
-      "supported",
-      "external",
-      "unsupported",
-      "unknown"
-    ],
-    "type": "string"
-  },
-  "title": {
-    "type": "string"
-  },
-  "updated_at": {
-    "type": "string"
-  }
-}
    • removedOutput schema / properties / datasets / items / required
      Removed value: -[
-  "dataset_id",
-  "title",
-  "asset_type",
-  "queryability",
-  "portal_url"
-]
    • removedOutput schema / properties / datasets / items / type
      Removed value: -"object"
    • addedOutput schema / properties / external_matches / items / $ref
      Added value: +"#/$defs/DatasetSummary"
    • removedOutput schema / properties / external_matches / items / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / external_matches / items / properties
      Removed value: -{
-  "asset_type": {
-    "type": "string"
-  },
-  "category": {
-    "type": "string"
-  },
-  "dataset_id": {
-    "type": "string"
-  },
-  "derived_from": {
-    "type": "string"
-  },
-  "description": {
-    "type": "string"
-  },
-  "external_url": {
-    "type": "string"
-  },
-  "guide_uri": {
-    "type": "string"
-  },
-  "portal_url": {
-    "type": "string"
-  },
-  "queryability": {
-    "enum": [
-      "supported",
-      "external",
-      "unsupported",
-      "unknown"
-    ],
-    "type": "string"
-  },
-  "title": {
-    "type": "string"
-  },
-  "updated_at": {
-    "type": "string"
-  }
-}
    • removedOutput schema / properties / external_matches / items / required
      Removed value: -[
-  "dataset_id",
-  "title",
-  "asset_type",
-  "queryability",
-  "portal_url"
-]
    • removedOutput schema / properties / external_matches / items / type
      Removed value: -"object"
    • removedOutput schema / properties / external_search_status / type
      Removed value: -"string"
    • removedOutput schema / properties / match_evidence / items / properties / matched_fields / items / type
      Removed value: -"string"
    • removedOutput schema / properties / source / properties / now_local_reason / type
      Removed value: -"string"
    • removedOutput schema / properties / source / properties / portal / properties / tier / type
      Removed value: -"string"
    • addedOutput schema / properties / truncated
      Added value: +{
+  "type": "boolean"
+}
    • addedOutput schema / properties / truncation_hint
      Added value: +{
+  "type": "string"
+}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial behavior beyond the read-only/open-world annotations: results are candidates only, match_evidence reveals missing query terms, external_matches are capped at 3 and are non-queryable, and typical latency is 1-3 s. This is exactly the kind of unstated operational context annotations cannot carry.

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?

Front-loaded with the purpose and the trigger condition, and every sentence carries information (scope, evidence semantics, latency). The middle lines are dense to the point of being cryptic without the schema in view, which keeps it short of a 5.

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?

With an output schema present, the description doesn't need to enumerate return fields, and it still clarifies the non-obvious ones (match_evidence, external_matches). For a 7-param, paginated, open-world search tool, 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.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all 7 params; the description still adds value by tying asset_scope to the external_matches behavior and showing a concrete call example with portal and query. It adds interpretation, not just repetition.

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+resource ('Find a portal's datasets by topic') and scopes it against siblings by naming the trigger condition ('Call when you lack a dataset id'), which implicitly contrasts with atlas_describe_dataset / atlas_query_dataset that need an id.

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 a clear when-to-use condition ('when you lack a dataset id') and downstream constraints on which results are usable. It doesn't explicitly name alternatives (atlas_find_portals for portal ids, atlas_query_dataset for querying), so the exclusions stay 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.

Deploy Server

Other Tools