Skip to main content
Glama

Bpstat Pt

by io.github.pipeworx-io

Ask Pipeworx — Grounded

ask_pipeworx_grounded
Read-onlyIdempotent

Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,801 across 1517 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoAlias for question.
textNoAlias for question.
inputNoAlias for question.
queryNoAlias for question.
promptNoAlias for question.
questionYesYour question in natural language. Accepts query, q, prompt, text, input as aliases.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

The description goes beyond annotations by detailing success (returns answer with verbatim evidence) and failure modes (refusal_reason enumerations such as not_in_source or tool_error), which is valuable behavioral transparency. It does not contradict the annotations (read-only, idempotent). It slightly under-specifies edge cases like data truncation, but overall strong.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately long but every sentence carries distinct information: purpose, routing similarity, output structure, refusal reasons, usage triggers, and cost trade-off. It is efficiently structured with a clear flow from what → how → when. Minor redundancy exists in repeating the cost trade-off but not enough to detract.

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

Completeness5/5

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 explains the return format (answer with evidence, or refusal with reason) and the conditions for each. It also addresses the key trade-off versus the sibling tool, making the context complete for an agent to decide and use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover 100% of parameters and identify aliases (q, text, input, query, prompt) but provide only minimal semantic detail ('Your question in natural language'). The tool description itself adds no further parameter nuance. This meets the baseline for full coverage but does not exceed it.

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's purpose as a hallucination-resistant answer mode for high-stakes reads, explicitly distinguishing it from the sibling ask_pipeworx by emphasizing evidence-based output and refusal behavior. It provides a specific verb ('answer') and resource ('source data'), leaving no ambiguity about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance ('Use whenever an answer will be quoted, cited, or acted on') and when-not-to-use guidance ('prefer ask_pipeworx for casual lookups'), along with the trade-off (extra LLM call). This precisely directs an agent on choosing between the grounded and non-grounded variants.

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

All Bpstat Pt 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
Disambiguation2/5

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.

Naming Consistency3/5

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.

Tool Count2/5

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.

Completeness3/5

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.

Resources