Skip to main content
Glama

Data Tours

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 5,798 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. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses important behavior: answers are extracted only from tool results, evidence is a verbatim quote, and failures produce explicit refusal reasons. It even lists all refusal_reason enum values. This gives the agent an accurate mental model of success and failure modes.

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 dense but every sentence contributes: mode, routing, extraction behavior, return structure, refusal reasons, usage guidance, and cost trade-off. It is front-loaded with the core purpose and then layers supporting detail. Slightly long, but justified for a tool with refusal behavior and sibling differentiation.

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?

Despite having no output schema, the description fully defines the success and refusal return shapes, lists concrete refusal reasons, explains the extra-call cost, and gives domain examples. An agent has enough information to invoke it correctly and interpret its response in all documented cases.

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 coverage is 100%, and the schema already documents the question parameter plus all aliases. The description adds context about how the question is processed, but no additional parameter-level semantics. Baseline 3 is appropriate because the schema carries the load.

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 defines the tool as a 'hallucination-resistant answer mode' for grounded question answering over Pipeworx data. It uses a specific verb+resource structure and explicitly contrasts itself with ask_pipeworx by noting the extra extraction step and refusal behavior. This gives an agent a clear identity distinct from siblings.

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 explicitly states when to use this tool: high-stakes reads, quoted/cited/acted-on answers, and domains where facts must not be invented. It also says to prefer ask_pipeworx for casual lookups because this variant costs an extra LLM call. This is strong, actionable usage routing with an explicit alternative.

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

All Data Tours 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

A4.2/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose. Even closely related tools like ask_pipeworx, ask_pipeworx_grounded, and deep_research are well-differentiated by their use cases and safety guarantees. The multiple polymarket tools each focus on a unique aspect (arbitrage, edge scanning, persistence, fill risk, cross-venue spreads), avoiding ambiguity.

Naming Consistency4/5

All tool names use lowercase with underscores, following a mostly verb_noun or domain_prefix_noun pattern (e.g., ask_pipeworx, entity_profile, resolve_entity). A few names like dataset_info and ai_visibility_check deviate slightly from a strict verb_noun structure, but the overall pattern is predictable and readable.

Tool Count4/5

With 33 tools, the server is on the heavier end of the well-scoped range. However, the count is justified by the breadth of functionality: data queries, prediction markets, entity resolution, memory, monitoring, and more. The tools each serve a specific purpose, and none feel redundant.

Completeness4/5

The tool surface covers a wide range of use cases including data retrieval, comparison, research, monitoring, and memory. Minor gaps exist (e.g., no tool for placing prediction market trades or creating/updating Tours Métropole datasets), but these are likely intentional scope choices. Core workflows are well-supported.

Resources