Skip to main content
Glama

Cso Ie

by io.github.pipeworx-io

Query Dataset

query_dataset
Read-onlyIdempotent

Read a FILTERED slice of a CSO table via JSON-RPC. Pass a map of dimension code -> array of category index values to keep (get the dimension codes and category index values from dataset_metadata). Returns JSON-stat 2.0 covering only the selected cells — far smaller than get_dataset.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
matrixYesMatrix code, e.g. "CPM01".
filtersYesMap of dimension code to an array of category index values to keep, e.g. {"STATISTIC":["CPM01C08"],"TLIST(M1)":["202512"]}. Dimensions you omit are returned in full. Time dimensions like TLIST(M1) use YYYYMM index values (e.g. "202512").

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: +[
+  {
+    "filters": {
+      "STATISTIC": [
+        "CPM01C08"
+      ],
+      "TLIST(M1)": [
+        "202512"
+      ]
+    },
+    "matrix": "CPM01"
+  },
+  {
+    "filters": {
+      "TLIST(A1)": [
+        "2023"
+      ]
+    },
+    "matrix": "QLF18"
+  }
+]
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, and open-world hints. The description adds valuable behavioral context: the result covers only the selected cells, omitted dimensions are returned in full, and time dimensions use YYYYMM index values. This goes beyond what annotations provide, though it doesn't address error handling or rate limits.

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 concise sentences that front-load the action and add key details about the filter mechanism and output size. Every sentence earns its place, and there is no wasted text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description explains the return type (JSON-stat 2.0), what it covers ('only the selected cells'), and how filters behave. It also directs users to dataset_metadata for codes. It is reasonably complete, though it could mention limits or error cases.

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?

Schema coverage is 100% with descriptions for both parameters. The description adds examples and elaborates on the structure of the filters map, including the time dimension format and the behavior of omitted dimensions. This meaningfully supplements 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 the tool reads a filtered slice of a CSO table via JSON-RPC. It uses a specific verb (read), names the resource (CSO table), and explicitly differentiates itself from get_dataset by noting the result is 'far smaller'. This makes the purpose unmistakable.

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 tells you how to use the tool (pass a map of dimension codes to category index values), where to get those codes (from dataset_metadata), and what happens when you omit dimensions ('returned in full'). It also contrasts with get_dataset ('far smaller'), implying when this tool is preferable. However, it doesn't explicitly state when not to use it or list alternatives beyond get_dataset.

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

All Cso Ie 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

A3.8/5.0
Disambiguation3/5

Several tools have overlapping purposes: the four ask_pipeworx variants all route to the same 5,581 tools (ask_pipeworx_beta is currently identical to stable), and the six polymarket_* tools have subtle boundaries between research, edges, and arbitrage that could cause misselection. That said, the descriptions are unusually detailed, and non-overlapping clusters (CSO table tools, memory tools, subscription tools) are clearly distinct.

Naming Consistency3/5

All names are snake_case and mostly verb-first (get_dataset, resolve_entity, validate_claim), but conventions are inconsistent: polymarket_* and pipeworx_* are brand/noun-first while bet_research and ask_pipeworx put the verb first for the same domains, and some tools are pure nouns (entity_profile, recent_alerts). The pattern is readable but far from predictable.

Tool Count2/5

At 35 tools the server is well past the 25+ 'too many' threshold for a single MCP. Several tools don't earn their place: ask_pipeworx_beta is functionally identical to ask_pipeworx right now, and the six polymarket tools plus four ask_pipeworx variants represent heavy redundancy for what are essentially two sub-domains.

Completeness4/5

The data-access core is covered end to end: discovery (discover_tools, list_datasets, suggest_questions), structured reads (ask_pipeworx, get_dataset, query_dataset), grounded verification (validate_claim, ask_pipeworx_grounded), comparison (compare_entities), change tracking (recent_changes), plus memory and subscription CRUD. Minor gaps: subscriptions can't be edited (only recreated) and unrelated utilities (generate_llms_txt, scan_dependency) dilute the focus rather than fill a real gap.

Resources