list_datasetsList the datasets within a statistical domain (use a domain id from list_domains). Returns a JSON-stat collection; each item has extension.id (the dataset id, a hex string) and extension.num_series. The dataset id feeds get_dataset. lang defaults to PT.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Language: "PT" (default) or "EN". | |
| domain_id | Yes | Domain id from list_domains, e.g. 3 (Balança de pagamentos). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "domain_id": 3,
+ "lang": "EN"
+ },
+ {
+ "domain_id": 15,
+ "lang": "PT"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, non-destructive behavior. Description adds return format details (JSON-stat collection with specific fields), which provides useful behavioral context beyond annotations.
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: first gives purpose and input, second gives output structure and chaining. No wasted words, 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?
No output schema, but description sufficiently explains return format and chaining. For a simple listing tool, this is adequately complete.
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%, so baseline is 3. Description adds a concrete example for domain_id (3 for Balança de pagamentos) and mentions lang default, but doesn't add substantial new meaning beyond 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 the tool lists datasets within a statistical domain, specifies the input source (domain id from list_domains), and differentiates from sibling tools like list_domains and get_dataset.
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 use a domain id from list_domains and mentions chaining to get_dataset. Also notes lang defaults to PT. No explicit 'when not to use', but context is clear.
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.
Multiple tool clusters are nearly indistinguishable: ask_pipeworx and ask_pipeworx_beta are explicitly documented as currently identical, scan_competitor_ai_presence is a thin wrapper over ai_visibility_check, and the five polymarket_* tools (edges, edge_tracker, arbitrage, fill_risk, kalshi_spread) share heavily overlapping edge-detection/fill-analysis concerns. entity_profile and recent_changes also both fan out to the same SEC/news/patents sources, so an agent must read full descriptions to avoid misselection.
The dominant pattern is imperative verb_first (list_datasets, get_dataset, resolve_entity, validate_claim, scan_dependency, subscribe), but there are notable deviations: noun-phrase names like entity_profile, recent_alerts, recent_changes, bet_research, and deep_research; the ask_pipeworx brand family sits awkwardly beside get_/search_ verbs; and the polymarket_* prefix family forms yet another convention. Names are readable and mostly self-explanatory, but no single consistent scheme is followed.
At 35 tools, this exceeds the 'too many (25+)' threshold, and the bloat is compounded by the server's nominal identity: despite being named 'Bpstat Pt' (Banco de Portugal statistics), only about 5 tools (list_domains, list_datasets, get_dataset, get_series_metadata) actually serve that domain. The other 30 tools span unrelated subsystems — Polymarket betting, npm dependency scanning, AI visibility audits, generic memory, and subscriptions — suggesting several products bundled into one server.
For the broader data-gateway interpretation, the lifecycle is well covered: discovery (discover_tools, suggest_questions), query (ask_pipeworx), grounded verification (ask_pipeworx_grounded, validate_claim), deep research (deep_research), profiles/comparisons (entity_profile, compare_entities), monitoring (recent_changes, subscribe/recent_alerts), and memory (remember/recall/forget). However, for the nominal Bpstat statistical domain there is no keyword search over series or datasets — navigation requires knowing domain/dataset ids in advance — and the extreme scatter across unrelated domains leaves each subsystem only partially developed.