dataset_columnsList the columns of a datos.gov.co dataset: field name (used in SoQL $select/$where), human label, and data type. Call this before query_dataset so you know which fields exist. datasetId is the Socrata 4x4 code from search_datasets.
| Name | Required | Description | Default |
|---|---|---|---|
| datasetId | Yes | Socrata 4x4 id, e.g. "gt2j-8ykr". |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "datasetId": "gt2j-8ykr"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. Description adds behavioral detail: returned fields include field name (used in SoQL $select/$where), human label, and data type—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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no redundancy. Every sentence serves a purpose: listing outputs and providing usage context. Front-loaded with key information.
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?
For a simple single-parameter tool without output schema, description covers purpose, return values, and usage sequence. Complete given complexity and structured fields.
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?
Schema coverage is 100%, but description adds meaning beyond schema by explaining datasetId as 'Socrata 4x4 id' and giving an example, helping agents understand the parameter's origin and format.
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?
Description uses specific verb 'List' and identifies the resource 'columns of a datos.gov.co dataset'. It clearly distinguishes from sibling tools like query_dataset and search_datasets by focusing on metadata retrieval.
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?
Explicitly instructs to call before query_dataset to know existing fields. Also explains datasetId source as Socrata 4x4 code from search_datasets, providing clear when-to-use and prerequisite context.
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.
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.
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.
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.
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.