Skip to main content
Glama

pg-aiguide

by io.github.timescale

Search Documentation

search_docs
Read-onlyIdempotent

Search documentation with hybrid semantic (vector) and keyword (BM25) search. Use semanticWeight to choose keyword-only (0), semantic-only (1), or a blend; mid values fuse rankings with RRF. Supports Tiger Cloud (TimescaleDB), PostgreSQL, and PostGIS.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitYesThe maximum number of matches to return. Defaults to 20.
queryYesThe search query. Used for BM25 when keyword or hybrid search applies, and for the embedding when semantic or hybrid search applies.
sourceYesThe documentation source to search. "tiger" for Tiger Cloud and TimescaleDB, "postgres" for PostgreSQL, "postgis" for PostGIS spatial extension. Specific versions provided with _X.X suffixes.
semanticWeightYesControls the balance between semantic and keyword search. 0 = keyword only, 0.5 = equal mix, 1 = semantic only. Default is 0.7 (favor semantic search).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultsYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed6 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"The maximum number of matches to return. If not provided, default is 10."New value: +"The maximum number of matches to return. Defaults to 20."
    • changedInput schema / properties / query / description
      Previous value: -"The search query. For semantic search, use natural language. For keyword search, provide keywords."New value: +"The search query. Used for BM25 when keyword or hybrid search applies, and for the embedding when semantic or hybrid search applies."
    • removedInput schema / properties / search_type
      Removed value: -{
-  "description": "The type of search to perform. \"semantic\" uses natural language vector similarity, \"keyword\" uses BM25 keyword matching.",
-  "enum": [
-    "semantic",
-    "keyword"
-  ],
-  "type": "string"
-}
    • addedInput schema / properties / semanticWeight
      Added value: +{
+  "anyOf": [
+    {
+      "maximum": 1,
+      "minimum": 0,
+      "multipleOf": 0.1,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Controls the balance between semantic and keyword search. 0 = keyword only, 0.5 = equal mix, 1 = semantic only. Default is 0.7 (favor semantic search)."
+}
    • changedInput schema / required
      Previous value: -[
-  "source",
-  "search_type",
-  "query",
-  "limit"
-]New value: +[
+  "source",
+  "query",
+  "limit",
+  "semanticWeight"
+]
    • changedOutput schema / properties / results / items / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "content": {
-        "description": "The content of the documentation entry.",
-        "type": "string"
-      },
-      "distance": {
-        "description": "The distance score indicating the relevance of the entry to the query. Lower values indicate higher relevance.",
-        "type": "number"
-      },
-      "id": {
-        "description": "The unique identifier of the documentation entry.",
-        "maximum": 9007199254740991,
-        "minimum": -9007199254740991,
-        "type": "integer"
-      },
-      "metadata": {
-        "description": "Additional metadata about the documentation entry, as a JSON encoded string.",
-        "type": "string"
-      }
-    },
-    "required": [
-      "id",
-      "content",
-      "metadata",
-      "distance"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "content": {
-        "description": "The content of the documentation entry.",
-        "type": "string"
-      },
-      "id": {
-        "description": "The unique identifier of the documentation entry.",
-        "maximum": 9007199254740991,
-        "minimum": -9007199254740991,
-        "type": "integer"
-      },
-      "metadata": {
-        "description": "Additional metadata about the documentation entry, as a JSON encoded string.",
-        "type": "string"
-      },
-      "score": {
-        "description": "The score indicating the relevance of the entry to the keywords. Higher values indicate higher relevance.",
-        "type": "number"
-      }
-    },
-    "required": [
-      "id",
-      "content",
-      "metadata",
-      "score"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "content": {
+        "description": "The content of the documentation entry.",
+        "type": "string"
+      },
+      "distance": {
+        "description": "The distance score indicating the relevance of the entry to the query. Lower values indicate higher relevance.",
+        "type": "number"
+      },
+      "id": {
+        "description": "The unique identifier of the documentation entry.",
+        "maximum": 9007199254740991,
+        "minimum": -9007199254740991,
+        "type": "integer"
+      },
+      "metadata": {
+        "description": "Additional metadata about the documentation entry, as a JSON encoded string.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "content",
+      "metadata",
+      "distance"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "content": {
+        "description": "The content of the documentation entry.",
+        "type": "string"
+      },
+      "id": {
+        "description": "The unique identifier of the documentation entry.",
+        "maximum": 9007199254740991,
+        "minimum": -9007199254740991,
+        "type": "integer"
+      },
+      "metadata": {
+        "description": "Additional metadata about the documentation entry, as a JSON encoded string.",
+        "type": "string"
+      },
+      "score": {
+        "description": "The score indicating the relevance of the entry to the keywords. Higher values indicate higher relevance.",
+        "type": "number"
+      }
+    },
+    "required": [
+      "id",
+      "content",
+      "metadata",
+      "score"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "content": {
+        "description": "The content of the documentation entry.",
+        "type": "string"
+      },
+      "id": {
+        "description": "The unique identifier of the documentation entry.",
+        "maximum": 9007199254740991,
+        "minimum": -9007199254740991,
+        "type": "integer"
+      },
+      "metadata": {
+        "description": "Additional metadata about the documentation entry, as a JSON encoded string.",
+        "type": "string"
+      },
+      "rrf_score": {
+        "description": "Hybrid search: fused RRF score from combining semantic and keyword result rankings.",
+        "type": "number"
+      }
+    },
+    "required": [
+      "id",
+      "content",
+      "metadata",
+      "rrf_score"
+    ],
+    "type": "object"
+  }
+]
  2. Changed9 schema fields changed
    • addedInput schema / properties / limit / anyOf
      Added value: +[
+  {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / limit / description
      Previous value: -"The maximum number of matches to return. Default is 10."New value: +"The maximum number of matches to return. If not provided, default is 10."
    • removedInput schema / properties / limit / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / limit / minimum
      Removed value: --9007199254740991
    • removedInput schema / properties / limit / type
      Removed value: -"integer"
    • changedInput schema / properties / source / description
      Previous value: -"The documentation source to search. \"tiger\" for Tiger Cloud and TimescaleDB, \"postgres\" for PostgreSQL, \"postgis\" for PostGIS spatial extension."New value: +"The documentation source to search. \"tiger\" for Tiger Cloud and TimescaleDB, \"postgres\" for PostgreSQL, \"postgis\" for PostGIS spatial extension. Specific versions provided with _X.X suffixes."
    • changedInput schema / properties / source / enum
      Previous value: -[
-  "tiger",
-  "postgres",
-  "postgis"
-]New value: +[
+  "tiger",
+  "postgres_14",
+  "postgres_15",
+  "postgres_16",
+  "postgres_17",
+  "postgres_18",
+  "postgis_3.3",
+  "postgis_3.4",
+  "postgis_3.5",
+  "postgis_3.6"
+]
    • removedInput schema / properties / version
      Removed value: -{
-  "anyOf": [
-    {
-      "enum": [
-        "14",
-        "15",
-        "16",
-        "17",
-        "18",
-        "latest"
-      ],
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "description": "The PostgreSQL major version (ignored when searching \"tiger\"). Recommended to assume the latest version if unknown. Only applicable when source is Postgres. Defaults to latest version."
-}
    • changedInput schema / required
      Previous value: -[
-  "source",
-  "search_type",
-  "query",
-  "version",
-  "limit"
-]New value: +[
+  "source",
+  "search_type",
+  "query",
+  "limit"
+]
  3. Changed4 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / limit / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / limit / minimum
      Added value: +-9007199254740991
    • changedOutput schema / properties / results / items / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "content": {
-        "description": "The content of the documentation entry.",
-        "type": "string"
-      },
-      "distance": {
-        "description": "The distance score indicating the relevance of the entry to the query. Lower values indicate higher relevance.",
-        "type": "number"
-      },
-      "id": {
-        "description": "The unique identifier of the documentation entry.",
-        "type": "integer"
-      },
-      "metadata": {
-        "description": "Additional metadata about the documentation entry, as a JSON encoded string.",
-        "type": "string"
-      }
-    },
-    "required": [
-      "id",
-      "content",
-      "metadata",
-      "distance"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "content": {
-        "$ref": "#/properties/results/items/anyOf/0/properties/content"
-      },
-      "id": {
-        "$ref": "#/properties/results/items/anyOf/0/properties/id"
-      },
-      "metadata": {
-        "$ref": "#/properties/results/items/anyOf/0/properties/metadata"
-      },
-      "score": {
-        "description": "The score indicating the relevance of the entry to the keywords. Higher values indicate higher relevance.",
-        "type": "number"
-      }
-    },
-    "required": [
-      "id",
-      "content",
-      "metadata",
-      "score"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "content": {
+        "description": "The content of the documentation entry.",
+        "type": "string"
+      },
+      "distance": {
+        "description": "The distance score indicating the relevance of the entry to the query. Lower values indicate higher relevance.",
+        "type": "number"
+      },
+      "id": {
+        "description": "The unique identifier of the documentation entry.",
+        "maximum": 9007199254740991,
+        "minimum": -9007199254740991,
+        "type": "integer"
+      },
+      "metadata": {
+        "description": "Additional metadata about the documentation entry, as a JSON encoded string.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "content",
+      "metadata",
+      "distance"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "content": {
+        "description": "The content of the documentation entry.",
+        "type": "string"
+      },
+      "id": {
+        "description": "The unique identifier of the documentation entry.",
+        "maximum": 9007199254740991,
+        "minimum": -9007199254740991,
+        "type": "integer"
+      },
+      "metadata": {
+        "description": "Additional metadata about the documentation entry, as a JSON encoded string.",
+        "type": "string"
+      },
+      "score": {
+        "description": "The score indicating the relevance of the entry to the keywords. Higher values indicate higher relevance.",
+        "type": "number"
+      }
+    },
+    "required": [
+      "id",
+      "content",
+      "metadata",
+      "score"
+    ],
+    "type": "object"
+  }
+]
  4. Changed4 schema fields changed
    • addedInput schema / properties / version / anyOf
      Added value: +[
+  {
+    "enum": [
+      "14",
+      "15",
+      "16",
+      "17",
+      "18",
+      "latest"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / version / description
      Previous value: -"The PostgreSQL major version (ignored when searching \"tiger\"). Recommended to assume the latest version if unknown."New value: +"The PostgreSQL major version (ignored when searching \"tiger\"). Recommended to assume the latest version if unknown. Only applicable when source is Postgres. Defaults to latest version."
    • removedInput schema / properties / version / enum
      Removed value: -[
-  "14",
-  "15",
-  "16",
-  "17",
-  "18",
-  "latest"
-]
    • removedInput schema / properties / version / type
      Removed value: -"string"
  5. Changed2 schema fields changed
    • changedInput schema / properties / source / description
      Previous value: -"The documentation source to search. \"tiger\" for Tiger Cloud and TimescaleDB, \"postgres\" for PostgreSQL."New value: +"The documentation source to search. \"tiger\" for Tiger Cloud and TimescaleDB, \"postgres\" for PostgreSQL, \"postgis\" for PostGIS spatial extension."
    • changedInput schema / properties / source / enum
      Previous value: -[
-  "tiger",
-  "postgres"
-]New value: +[
+  "tiger",
+  "postgres",
+  "postgis"
+]
  6. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent), the description discloses the hybrid search mechanism, BM25, semantic vectors, RRF fusion for mid values, and supported database platforms. This adds substantial behavioral context without contradicting annotations.

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 two sentences, front-loaded with the core purpose, and every piece of information earns its place. No fluff or redundancy.

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 presence of an output schema and detailed annotations, the description sufficiently covers the tool's functionality, parameter tuning, and supported sources. It does not need to detail return values since the output schema exists.

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?

The schema already covers all parameters, but the description adds meaning by explaining the semanticWeight scale and that query is used for both BM25 and embedding where relevant. This goes beyond simple parameter names.

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 searches documentation using hybrid semantic and keyword search, which is a specific verb+resource combination. It also distinguishes from the sibling tool view_skill by focusing on search rather than viewing.

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?

The description provides explicit guidance on using semanticWeight values (0, 1, blend) and lists supported sources. However, it does not explicitly contrast with view_skill or state when not to use this tool, so it lacks full alternative guidance.

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

All pg-aiguide toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

search_docs and view_skill are largely distinct: one performs hybrid documentation search, the other retrieves a specific named skill. There is some overlap because both are information-retrieval entry points, but the descriptions provide clear enough usage boundaries.

Naming Consistency5/5

Both tools follow a consistent verb_noun snake_case pattern: search_docs and view_skill. The naming is predictable and aligned with the server's retrieval-focused purpose.

Tool Count3/5

Two tools is a thin surface for a server covering PostgreSQL, TimescaleDB, and PostGIS guidance. However, search_docs plus view_skill forms a minimal but functional knowledge-retrieval pair, so it sits at the borderline rather than being clearly insufficient.

Completeness4/5

The pair covers the main needs of a guide server: finding relevant documentation and retrieving detailed skill content. The available skills are exposed as metadata, which mitigates the lack of a dedicated list_skills tool; minor browsing gaps remain.

Resources