Skip to main content
Glama

ThinAir Data

by co.thinair.data
OverviewDiscussionsAdmin

query_sql

Read-onlyIdempotent

Execute a read-only SQL query against the target connection. ONLY SELECT / WITH / EXPLAIN permitted. Write dialect-appropriate SQL for the connection's engine — use PostgreSQL syntax for postgres connections (SELECT NOW(), LIMIT, ILIKE), T-SQL for mssql (SELECT GETDATE(), TOP N, LIKE), MySQL for mysql (SELECT NOW(), LIMIT). Response meta includes connection + dialect so you know which syntax worked; reuse that dialect in follow-up calls. Default LIMIT 100 unless the user asks for all rows.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax rows to return (default 100, max 1000)
queryYesSQL SELECT query to execute
connectionNoTarget connection name from this tenant's inventory. Call `list_connections` to see every name + dialect, then match semantically to the user's intent (e.g. 'analytics' → a connection named `*-analytics-*`; 'prod' → a connection with `prod-` prefix). If the user didn't specify, use the tenant's default (first added). Do not invent names — resolve from `list_connections` output.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
metaNo
displayNo
summaryNo
insightsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / data / anyOf
      Previous value: -[
-  {
-    "items": {
-      "additionalProperties": {},
-      "type": "object"
-    },
-    "type": "array"
-  },
-  {
-    "additionalProperties": true,
-    "properties": {
-      "code": {
-        "type": "string"
-      },
-      "details": {
-        "additionalProperties": {},
-        "type": "object"
-      },
-      "error": {
-        "type": "string"
-      },
-      "internal_code": {
-        "type": "string"
-      },
-      "message": {
-        "type": "string"
-      },
-      "retry_after_s": {
-        "type": "number"
-      }
-    },
-    "type": "object"
-  }
-]New value: +[
+  {
+    "items": {
+      "additionalProperties": {},
+      "type": "object"
+    },
+    "type": "array"
+  },
+  {
+    "additionalProperties": true,
+    "properties": {
+      "code": {
+        "type": "string"
+      },
+      "details": {
+        "additionalProperties": {},
+        "type": "object"
+      },
+      "error": {
+        "type": "string"
+      },
+      "internal_code": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "retry_after_s": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]
  2. Changed4 schema fields changed
    • addedInput schema / properties / connection / maxLength
      Added value: +256
    • addedInput schema / properties / limit / maximum
      Added value: +1000
    • addedInput schema / properties / limit / minimum
      Added value: +1
    • addedInput schema / properties / query / maxLength
      Added value: +50000
  3. Changed2 schema fields changed
    • addedOutput schema / properties / display / properties / map
      Added value: +{
+  "additionalProperties": true,
+  "properties": {
+    "label": {
+      "type": "string"
+    },
+    "lat": {
+      "type": "string"
+    },
+    "lon": {
+      "type": "string"
+    },
+    "title": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
    • changedOutput schema / properties / display / properties / type / anyOf
      Previous value: -[
-  {
-    "enum": [
-      "table",
-      "chart",
-      "metric",
-      "code",
-      "text",
-      "list"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "string"
-  }
-]New value: +[
+  {
+    "enum": [
+      "table",
+      "chart",
+      "metric",
+      "code",
+      "text",
+      "list",
+      "map"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "string"
+  }
+]
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "data": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": {},
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "additionalProperties": true,
+          "properties": {
+            "code": {
+              "type": "string"
+            },
+            "details": {
+              "additionalProperties": {},
+              "type": "object"
+            },
+            "error": {
+              "type": "string"
+            },
+            "internal_code": {
+              "type": "string"
+            },
+            "message": {
+              "type": "string"
+            },
+            "retry_after_s": {
+              "type": "number"
+            }
+          },
+          "type": "object"
+        }
+      ]
+    },
+    "display": {
+      "additionalProperties": true,
+      "properties": {
+        "chart": {
+          "additionalProperties": true,
+          "properties": {
+            "chartType": {
+              "type": "string"
+            },
+            "color": {
+              "type": "string"
+            },
+            "title": {
+              "type": "string"
+            },
+            "x": {
+              "type": "string"
+            },
+            "xLabel": {
+              "type": "string"
+            },
+            "y": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "items": {
+                    "type": "string"
+                  },
+                  "type": "array"
+                }
+              ]
+            },
+            "yLabel": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "code": {
+          "additionalProperties": true,
+          "properties": {
+            "executable": {
+              "type": "boolean"
+            },
+            "language": {
+              "anyOf": [
+                {
+                  "enum": [
+                    "sql",
+                    "json",
+                    "bash",
+                    "typescript"
+                  ],
+                  "type": "string"
+                },
+                {
+                  "type": "string"
+                }
+              ]
+            },
+            "title": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "metric": {
+          "additionalProperties": true,
+          "properties": {
+            "label": {
+              "type": "string"
+            },
+            "status": {
+              "anyOf": [
+                {
+                  "enum": [
+                    "good",
+                    "warning",
+                    "critical"
+                  ],
+                  "type": "string"
+                },
+                {
+                  "type": "string"
+                }
+              ]
+            },
+            "trend": {
+              "anyOf": [
+                {
+                  "enum": [
+                    "up",
+                    "down",
+                    "neutral"
+                  ],
+                  "type": "string"
+                },
+                {
+                  "type": "string"
+                }
+              ]
+            },
+            "trendValue": {
+              "type": "string"
+            },
+            "unit": {
+              "type": "string"
+            },
+            "value": {
+              "type": [
+                "string",
+                "number"
+              ]
+            }
+          },
+          "type": "object"
+        },
+        "type": {
+          "anyOf": [
+            {
+              "enum": [
+                "table",
+                "chart",
+                "metric",
+                "code",
+                "text",
+                "list"
+              ],
+              "type": "string"
+            },
+            {
+              "type": "string"
+            }
+          ]
+        }
+      },
+      "type": "object"
+    },
+    "insights": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "column": {
+            "type": "string"
+          },
+          "message": {
+            "type": "string"
+          },
+          "severity": {
+            "anyOf": [
+              {
+                "enum": [
+                  "info",
+                  "warning",
+                  "critical"
+                ],
+                "type": "string"
+              },
+              {
+                "type": "string"
+              }
+            ]
+          },
+          "value": {}
+        },
+        "required": [
+          "severity",
+          "message"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "meta": {
+      "additionalProperties": true,
+      "properties": {
+        "cacheHit": {
+          "type": "boolean"
+        },
+        "connection": {
+          "type": "string"
+        },
+        "dialect": {
+          "anyOf": [
+            {
+              "enum": [
+                "postgres",
+                "mysql",
+                "mssql"
+              ],
+              "type": "string"
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        "executionTimeMs": {
+          "type": [
+            "number",
+            "string"
+          ]
+        },
+        "plan": {},
+        "rowCount": {
+          "$ref": "#/properties/meta/properties/executionTimeMs"
+        },
+        "tool": {
+          "type": "string"
+        },
+        "truncated": {
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "summary": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  5. First observed

TDQS

A5/5.0
Behavior5/5

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

Annotations declare readOnlyHint, openWorldHint, and idempotentHint. The description reinforces the read-only nature ('ONLY SELECT / WITH / EXPLAIN permitted') and adds critical behavioral details: the response meta includes connection + dialect, which the agent can use to adapt subsequent calls. It also discloses the default limit and the cap of 1000. This goes well beyond the annotations, providing concrete runtime 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?

The description is a single dense paragraph that front-loads the core purpose ('Execute a read-only SQL query') and immediately states the constraint (ONLY SELECT/WITH/EXPLAIN). Each subsequent sentence adds a distinct, essential piece of guidance (dialect, response meta, limit, connection selection). There is no filler or redundancy; every sentence earns its place.

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?

For a SQL execution tool with three parameters, 100% schema coverage, and an output schema, the description covers all the essentials: the allowed operations, dialect handling, default and maximum limits, connection resolution, and the feedback mechanism (response meta). The agent has everything needed to select the right connection, write appropriate SQL, and interpret the result. No critical guidance is missing.

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?

The schema already documents all three parameters (query, limit, connection) with descriptions, but the tool description adds substantial practical guidance. For 'connection', it explains how to discover valid values via list_connections and how to match them semantically to user intent. For 'limit', it clarifies the default value. This goes beyond the schema's static field descriptions, significantly improving the agent's ability to invoke the tool correctly.

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's purpose: 'Execute a read-only SQL query against the target connection.' It specifies the allowed statement types (SELECT/WITH/EXPLAIN) and differentiates itself from siblings like cross_db_query by focusing on a single target connection. This is a specific, unambiguous definition that leaves no doubt about what the tool does.

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, actionable usage guidance: it instructs the agent to write dialect-appropriate SQL (with examples for PostgreSQL, T-SQL, MySQL), sets a default LIMIT of 100, and tells the agent to reuse the dialect from the response meta in follow-up calls. It also gives detailed instructions for selecting the 'connection' parameter by resolving it via list_connections. These are clear when-to-use and how-to-use instructions.

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

All ThinAir Data 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