query_datasetFetch rows from a dataset. Supports limit, offset, and filter map (column → value).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 1-10000 (default 100) | |
| offset | No | 0-based row offset | |
| filters | No | Column-value filter map | |
| dataset_id | Yes | Dataset ID |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesPrevious value: -[
- {
- "dataset_id": "d_8b84c4ee58e3cfc0ece0d773c8ca6abc"
- },
- {
- "dataset_id": "d_8b84c4ee58e3cfc0ece0d773c8ca6abc",
- "filters": {
- "region": "central"
- },
- "limit": 500,
- "offset": 0
- }
-]New value: +[
+ {
+ "dataset_id": "d_8b84c4ee58e3cfc0ece0d773c8ca6abc"
+ },
+ {
+ "dataset_id": "d_8b84c4ee58e3cfc0ece0d773c8ca6abc",
+ "filters": {
+ "town": "BEDOK"
+ },
+ "limit": 500,
+ "offset": 0
+ }
+]Input schema / examplesAdded value: +[
+ {
+ "dataset_id": "d_8b84c4ee58e3cfc0ece0d773c8ca6abc"
+ },
+ {
+ "dataset_id": "d_8b84c4ee58e3cfc0ece0d773c8ca6abc",
+ "filters": {
+ "region": "central"
+ },
+ "limit": 500,
+ "offset": 0
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "description": "Rows and metadata from dataset query",
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, and non-destructive behavior, so the description does not need to re-cover those. It adds a small amount of context by explaining the filter map structure, but it does not disclose any additional behavioral traits such as result formatting or pagination. This is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that front-loads the core purpose and then lists supported features. Every word adds value, with no fluff or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of a rich output schema and comprehensive annotations, the description is sufficiently complete for a simple read tool. It covers purpose, key parameters, and the filtering capability. Minor gaps include not mentioning openWorldHint implications or explicit pagination details, but these are not critical given the schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides detailed descriptions for all parameters (coverage 100%), so the baseline is 3. The description's mention of 'limit, offset, and filter map' duplicates what the schema states and adds no new information, only reinforcing the filter map's column-to-value behavior already in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Fetch rows from a dataset' with a specific verb and resource, and distinguishes this tool from siblings like get_dataset or search_datasets by focusing on row-level access with filtering. It also mentions the key supported parameters, making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context for use: fetching rows with limit, offset, and filters. However, it does not explicitly mention when not to use it or name alternatives like get_dataset or search_within, so it lacks exclusions but still provides adequate contextual guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
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.
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.
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.
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.