Georgia Civic Data

Search Datasets

search_datasets

Read-onlyIdempotent

Search the catalog by meaning and keywords: dataset names, titles, everyday search phrases in English and Spanish, summaries, descriptions, and column names and descriptions. Plain wording works ('kids missing school', 'jobless', 'desempleo'), as do acronyms ('ap', 'el', 'ib'). Returns short dataset summaries, best first, with the fields and columns that matched, a confidence of 'high', 'medium' or 'low' (low: nothing in the catalog may fit), plus dimension_matches when a lookup table fits (e.g. 'school directory'). main_topic, level and year narrow the results to datasets that have them. The query text is sent to Voyage AI to compute its meaning; the results come only from this catalog.

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": {
      "query": "<query>"
    },
    "name": "search_datasets"
  }
}

Input Schema

Name	Required	Description
`year`	No	Only datasets with data for this year. Omit for all.
`level`	No	Only datasets published at this geographic level: 'states', 'counties', 'districts', 'schools', 'tracts' or 'block_groups' (singular forms work). Omit for all.
`limit`	No	Most results to return (default 20, at most 100).
`query`	Yes	What to look for, e.g. 'graduation rate'.
`main_topic`	No	Only datasets in this subject area. Omit for all.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 2, 2026

addedInput schema / properties / level

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Only datasets published at this geographic level: 'states', 'counties', 'districts', 'schools', 'tracts' or 'block_groups' (singular forms work). Omit for all.",
+  "title": "Level"
+}

addedInput schema / properties / main_topic

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Only datasets in this subject area. Omit for all.",
+  "enum": [
+    "census",
+    "education",
+    "health",
+    "immigration",
+    null
+  ],
+  "title": "Main Topic"
+}

changedInput schema / properties / query / description

Previous value: -"Words to search for, e.g. 'graduation rate'."New value: +"What to look for, e.g. 'graduation rate'."

addedInput schema / properties / year

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Only datasets with data for this year. Omit for all.",
+  "title": "Year"
+}

Changed4 schema fields changedOct 26, 2026
- addedInput schema / properties / limit / description
```
Added value: +"Most results to return (default 20, at most 100)."
```
- addedInput schema / properties / limit / maximum
```
Added value: +100
```
- addedInput schema / properties / limit / minimum
```
Added value: +1
```
- addedInput schema / properties / query / description
```
Added value: +"Words to search for, e.g. 'graduation rate'."
```
First observedSep 7, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond standard read-only hints, it describes the operational behavior of the results: the tool uses Voyage AI for semantic computation, and the output includes specific fields like a 'confidence' level and 'dimension_matches' count.

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?

The description is highly detailed and comprehensive, though slightly long, every section contributes unique, necessary context about the tool's capabilities and limitations.

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?

Given the semantic nature of the search, the description covers the technology stack, scope (the catalog), expected result structure (summaries, confidence), and available filtering options, making it contextually complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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

While the schema is 100% covered, the description adds crucial usage context, especially for the 'query' parameter, explaining that plain wording, acronym usage ('ap', 'el'), and regional language usage (Spanish) are supported.

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?

The description clearly states the tool performs a semantic search of the catalog using keywords, titles, and column names, distinguishing it from simple listing or structured querying siblings.

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

Usage Guidelines5/5

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

The description provides explicit instructions on how to query effectively, such as using plain language, handling synonyms (English and Spanish), and how to narrow results using optional parameters like main_topic and level.

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

All Georgia Civic Data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?