Skip to main content
Glama

Data Mo

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Query

query
Read-onlyIdempotent

Run a Socrata SoQL query against a Missouri Open Data dataset by resource_id (e.g. "gfq7-aa86"). Filter with where/select/group/order (SoQL clauses, without the leading $) plus limit/offset. Returns matching rows as JSON.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
groupNoSoQL $group column(s).
limitNoMax rows (default Socrata 1000).
orderNoSoQL $order, e.g. "date DESC".
whereNoSoQL $where filter, e.g. "year >= 2020 AND status = 'Active'".
offsetNoPagination offset.
selectNoSoQL $select, e.g. "name, count(*) AS n".
resource_idYesDataset id, e.g. "gfq7-aa86" (from datasets).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "limit": 100,
-    "resource_id": "gfq7-aa86",
-    "where": "year >= 2020"
-  },
-  {
-    "group": "category",
-    "order": "n DESC",
-    "resource_id": "gfq7-aa86",
-    "select": "name, count(*) AS n"
-  }
-]New value: +[
+  {
+    "limit": 20,
+    "resource_id": "gfq7-aa86"
+  },
+  {
+    "limit": 20,
+    "resource_id": "gfq7-aa86",
+    "select": "solicitor_number"
+  }
+]
  2. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "limit": 100,
+    "resource_id": "gfq7-aa86",
+    "where": "year >= 2020"
+  },
+  {
+    "group": "category",
+    "order": "n DESC",
+    "resource_id": "gfq7-aa86",
+    "select": "name, count(*) AS n"
+  }
+]
  3. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds the return format ('rows as JSON') and the convention that SoQL clauses are passed without the leading '$', which is genuinely useful, but says nothing about auth, rate limits, or result-size behavior.

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

Conciseness5/5

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

Three tight sentences: what it does, how to filter, what comes back. Zero filler and the verb/resource lead is front-loaded.

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

Completeness4/5

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

With no output schema, the description correctly states the return shape (JSON rows), and all 7 parameters are covered by the schema. It is close to complete, though it omits how to obtain a resource_id (the schema's parenthetical '(from datasets)' does that work instead of the description).

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 per-parameter docs already carry the detail; the description still adds a real semantic rule that the schema only hints at by using '$' notation - the clauses must be passed WITHOUT the leading '$'. It also enumerates the filterable clauses (where/select/group/order/limit/offset) in one place.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Run a Socrata SoQL query against a Missouri Open Data dataset'. The naming ('query') is generic, and the description doesn't contrast this with the many sibling tools, but the resource_id example ('gfq7-aa86') pins down exactly what it operates on.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: it tells you the dataset is addressed by resource_id and that filtering params exist, but gives no explicit when-to-use/when-not, no prerequisites, and no pointers to siblings like 'datasets' for discovering a resource_id or 'metadata' for schema discovery.

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

All Data Mo toolsInspect
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