list_domainsList Banco de Portugal's statistical domains (the full subject tree). Each domain has id, parent_id (tree links; null = top level), label/short_label/description (Portuguese by default), num_series, num_datasets, and has_series. Start here, then use a domain id with list_datasets. lang defaults to PT; pass "EN" for English.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Language: "PT" (default) or "EN". |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "lang": "EN"
+ },
+ {
+ "lang": "PT"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds that it returns hierarchical data with parent_id, and describes returned fields. This goes beyond annotations but is not critical for safety.
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, front-loaded with purpose, no filler. Every sentence adds value: first defines the tool, second details output and workflow.
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 one optional parameter and no output schema, the description fully explains what the response contains (id, parent_id, labels, counts) and how to proceed. No missing context for a listing tool.
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% with a single 'lang' parameter. The description mentions 'lang defaults to PT; pass "EN" for English', which repeats the schema's description without adding new syntactic or semantic details. Minimal added value.
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 statistical domains from Banco de Portugal, specifying it returns the full subject tree with fields like id, parent_id, labels, and counts. It distinguishes itself from sibling 'list_datasets' by advising to start here and then use a domain id with list_datasets.
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 says 'Start here, then use a domain id with list_datasets', providing clear workflow guidance. Also explains lang parameter default (PT) and how to switch to English, leaving no ambiguity about when and how to use.
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.