Skip to main content
Glama

Data Gov Sg

by io.github.pipeworx-io

Search Datasets

search_datasets
Read-onlyIdempotent

Search the data.gov.sg dataset catalog by keyword (e.g. "rainfall", "hawker centres", "resale flat prices") — real text search via data.gov.sg's own site search, since the official v2 catalog API has none. Returns matching COLLECTIONS (topics that may bundle several datasets, e.g. one per year) with each dataset's real dataset_id for get_dataset / query_dataset. Omit query to browse the raw catalog unfiltered instead, paged 10/page (~4,600 datasets total).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo1-based page (10 results per page either way)
queryNoKeyword search, e.g. "rainfall", "COE prices", "population". Omit to browse unfiltered.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

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

  1. Changed3 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "page": 1
-  },
-  {
-    "page": 2
-  }
-]New value: +[
+  {
+    "query": "rainfall"
+  },
+  {
+    "page": 1
+  }
+]
    • changedInput schema / properties / page / description
      Previous value: -"1-based page (10 datasets per page; the upstream fixes the page size)"New value: +"1-based page (10 results per page either way)"
    • addedInput schema / properties / query
      Added value: +{
+  "description": "Keyword search, e.g. \"rainfall\", \"COE prices\", \"population\". Omit to browse unfiltered.",
+  "type": "string"
+}
  2. Changed4 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "query": "weather"
-  },
-  {
-    "page": 1,
-    "page_size": 50,
-    "query": "traffic"
-  }
-]New value: +[
+  {
+    "page": 1
+  },
+  {
+    "page": 2
+  }
+]
    • changedInput schema / properties / page / description
      Previous value: -"1-based page (default 1)"New value: +"1-based page (10 datasets per page; the upstream fixes the page size)"
    • removedInput schema / properties / page_size
      Removed value: -{
-  "description": "1-100 (default 20)",
-  "type": "number"
-}
    • removedInput schema / properties / query
      Removed value: -{
-  "description": "Free-text filter",
-  "type": "string"
-}
  3. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "query": "weather"
+  },
+  {
+    "page": 1,
+    "page_size": 50,
+    "query": "traffic"
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "description": "Dataset search results from data.gov.sg catalog",
+  "type": "object"
+}
  4. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already mark this as safe/read-only/idempotent, and the description adds substantial behavioral value: it reveals that search returns COLLECTIONS (potentially bundling datasets), that the official API has no search, that results include real dataset_ids, and that pagination is 10/page. These details materially change how an agent would interpret and use results.

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 dense sentences front-load the purpose with examples, then provide necessary behavioral nuance (collections, page size, total count, browse mode). Every sentence earns its place with no wasted words or redundant schema repetition.

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 two-optional-parameter tool with an output schema and strong annotations, the description covers all important ground: search semantics, output shape (collections with dataset_ids), pagination, and an alternative browse mode. An agent has enough context to invoke and interpret this tool 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?

The input schema already documents both parameters fully (100% coverage). The description adds helpful semantic context, such as example queries, the page size, and the 'omit query to browse' behavior, beyond what the schema states. This reinforces but does not redundantly repeat the schema.

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?

Clearly identifies the action (Search) and resource (data.gov.sg dataset catalog), gives concrete examples, and distinguishes itself from sibling tools by explaining it returns real dataset_id values for get_dataset/query_dataset. The phrase 'real text search' adds specificity beyond a generic catalog lookup.

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?

Provides clear context: use for keyword search of the catalog, and mentions an alternative mode (omit query to browse). It also links to downstream tools (get_dataset/query_dataset) for follow-up use. Lacks an explicit 'when not to use' or named alternative like search_within, but the guidance is otherwise strong.

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

All Data Gov Sg 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

A3.6/5.0
Disambiguation2/5

Several tools have heavily overlapping purposes: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, and the Polymarket and company-research toolsets overlap significantly (bet_research vs polymarket_edges, entity_profile vs compare_entities vs recent_changes). Even with strong descriptions, an agent can easily misselect among these near-duplicate entry points.

Naming Consistency3/5

Names are readable but mix conventions: verb_noun forms (search_datasets, query_dataset, generate_llms_txt, validate_claim) coexist with noun/adjective forms (air_quality_pm25, taxi_availability, entity_profile, polymarket_edges). There is no single predictable pattern, though the domain-prefix style for Singapore data tools is consistent.

Tool Count2/5

40 tools is far too many for a server nominally scoped to Singapore government data. The bulk of the surface is a general-purpose Pipeworx/prediction-market/research toolkit that has nothing to do with Data Gov Sg, so the actual Singapore dataset tools are buried under dozens of unrelated capabilities.

Completeness4/5

For the core data.gov.sg use case, the surface is solid: search_datasets, get_dataset, and query_dataset cover dataset discovery and retrieval, supplemented by live-data tools (weather_now, air_quality_psi, traffic_incidents, taxi_availability, uv_index). The broader Pipeworx side also includes helpful auxiliary lifecycle tools like discover, subscribe, recent_alerts, memory, and feedback, so there are no critical dead ends.

Resources