Skip to main content
Glama

Datos Co

by io.github.pipeworx-io

Query Dataset

query_dataset
Read-onlyIdempotent

Query rows from a datos.gov.co dataset using SoQL. datasetId is the Socrata 4x4 code from search_datasets. SoQL clauses: $select (columns / aggregates like "count(*)"), $where (SQL-like filter, e.g. "departamento_nom='BOGOTA' AND edad > 60"), $order ("count desc"), $group, $q (full-text across the row). Use dataset_columns first to learn field names. Returns an array of row objects keyed by field name. Default $limit is 50 (Socrata max per page is 50000).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
$qNoFull-text search across the whole row.
$groupNoGroup-by field(s) for aggregation.
$limitNoRows to return (default 50).
$orderNoSort, e.g. "fecha_reporte_web desc".
$whereNoSQL-like filter, e.g. "edad > 60 AND sexo='F'".
$offsetNoPagination offset (default 0).
$selectNoColumns or aggregates, e.g. "departamento_nom, count(*)".
datasetIdYesSocrata 4x4 id, e.g. "gt2j-8ykr".

Schema Changelog

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

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "$group": "departamento_nom",
+    "$order": "count desc",
+    "$select": "departamento_nom, count(*)",
+    "datasetId": "gt2j-8ykr"
+  },
+  {
+    "$limit": 100,
+    "$select": "fecha, valor",
+    "$where": "departamento_nom='BOGOTA' AND fecha >= '2023-01-01'",
+    "datasetId": "gt2j-8ykr"
+  }
+]
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false. Description adds details: default limit 50, max per page 50000, returns array of row objects keyed by field name. No contradiction.

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?

Concise and well-structured. Front-loads main purpose, then lists SoQL clauses, then references dataset_columns, then return format and default limit. No waste.

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 8 parameters and SoQL complexity, description covers usage, parameters, defaults, and return format. References sibling tools. No output schema, but return format is described.

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?

Schema coverage is 100%. Description explains each SoQL clause with examples (e.g., $select, $where, $order, $group) and their purpose, adding significant meaning beyond 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?

The description clearly states 'Query rows from a datos.gov.co dataset using SoQL.' It distinguishes from siblings like dataset_columns (learn field names) and search_datasets (find dataset IDs) by specifying the action and resource.

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 guidance: use search_datasets first to get datasetId, use dataset_columns to learn field names before querying. Includes SoQL syntax and examples. Does not explicitly mention when not to use, but context is sufficient.

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

All Datos Co 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

A3.9/5.0
Disambiguation3/5

Most tools have distinct purposes, but several natural-language query tools (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, validate_claim) occupy overlapping territory, and ask_pipeworx_beta is explicitly identical to ask_pipeworx right now. The prediction-market cluster (polymarket_edges, polymarket_arbitrage, bet_research, polymarket_fill_risk, polymarket_edge_tracker, polymarket_kalshi_spread) also has fuzzy boundaries, though the long descriptions help an agent differentiate.

Naming Consistency3/5

Names are consistently lowercase with underscores, and there are coherent subfamilies like ask_pipeworx*, polymarket_*, and scan_*. However, the overall set mixes conventions: verb_noun (query_dataset, resolve_entity), noun_noun (entity_profile, bet_research), adjective_noun (recent_changes), and bare verbs (remember, recall, forget), so no single predictable pattern governs the server.

Tool Count2/5

34 tools is a heavy surface for one server, including multiple meta/onboarding utilities (discover_tools, suggest_questions, pipeworx_feedback, pipeworx_trending) and a large prediction-market subcluster. The count exceeds the 25-tool threshold where a tool set typically becomes unwieldy, and several tools could be consolidated or split into separate servers.

Completeness4/5

For a read-heavy data research platform, the surface is very complete: discovery, routed lookup, grounded verification, entity resolution, profiles, comparisons, change feeds, dataset querying, prediction-market research, and full memory/subscription lifecycles are all covered. Minor gaps exist, such as no explicit pipeworx:// URI read tool and no subscription update operation, but agents can work around them.

Resources