dataset_metadataGet the structure of one CSO table by matrix code: its dimensions, the category codes + human labels for each dimension, size, and last-updated date. Use this to discover valid dimension codes before calling get_dataset with filters.
| Name | Required | Description | Default |
|---|---|---|---|
| matrix | Yes | Matrix code, e.g. "CPM01" (Consumer Price Index) or "QLF18" (labour force). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "matrix": "CPM01"
+ },
+ {
+ "matrix": "QLF18"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive behavior, so the description adds value by disclosing the concrete outputs: dimensions, category codes, human labels, size, and last-updated date. This contextualizes what to expect from the call.
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 sentences: the first explains the tool's purpose and output, the second gives usage guidance. Every word earns its place; no redundancy or padding.
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 no output schema, the description sufficiently enumerates what the tool returns and when to use it. The single parameter and read-only nature are already covered by schema and annotations, leaving no significant gaps.
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 fully documents the 'matrix' parameter with type and examples (CPM01, QLF18). The description adds minimal semantic value beyond confirming that the parameter is a matrix code, but this is acceptable given 100% schema coverage.
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 the tool's function: 'Get the structure of one CSO table by matrix code' and lists the returned components. It distinguishes itself from siblings by mentioning 'before calling get_dataset with filters', positioning this as the metadata lookup step.
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?
Explicit usage guidance is provided: 'Use this to discover valid dimension codes before calling get_dataset with filters.' This tells the agent exactly when to use this tool and names the related sibling (get_dataset) where this metadata is a prerequisite.
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 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.
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.
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.
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.