Skip to main content
Glama

EUR-Lex

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 5,743 across 1500 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.

TDQS

A4.7/5.0
Behavior5/5

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

The description adds substantial behavioral detail beyond the annotations: it explains the tool extracts answers only from tool result content, returns a structured success object with evidence/confidence/source, and explicitly refuses rather than guessing, listing all possible refusal_reason values. This is highly transparent for a read-only tool.

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

Conciseness5/5

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

Every sentence earns its place: purpose, routing behavior, success/refusal return contract, when to use, and cost tradeoff. The description is front-loaded with the core purpose and then structured logically without redundancy or filler.

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 details the full success response shape and all refusal reasons, making return behavior fully predictable. Combined with explicit usage context, alternative preference, and cost consideration, the agent has everything needed to select and invoke 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?

The input schema already provides 100% coverage by documenting question and all aliases as natural-language question inputs. The description does not need to add parameter-level detail; the schema carries the full semantic load, so the baseline score of 3 is appropriate.

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 identifies this as a hallucination-resistant, grounded answer mode that routes like ask_pipeworx but extracts answers only from tool results. It specifies the resource (Pipeworx tool ecosystem) and differentiates it from the plain ask_pipeworx sibling by the grounded-evidence behavior and return format.

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?

Usage guidance is explicit: use when an answer will be quoted, cited, or acted on and facts must not be invented, with concrete examples like financial verdicts, legal claims, medical lookups, and public statements. It also gives a clear when-not by stating to prefer ask_pipeworx for casual lookups due to the extra LLM call.

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

All EUR-Lex 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

A3.7/5.0
Disambiguation1/5

Multiple tools appear to do nearly the same thing: ask_pipeworx, ask_ipeworx_beta (explicitly identical at the moment), ask_pipeworx_grounded, deep_research, and validate_claim all route questionanswering in a very similar way. Even with long descriptions, the sheer number of overlapping query/research/analysis tools (ai_visibility_check vs scan_comperitor_ai_presence, all polymarket_*) would make an agent uncertain which to call.

Naming Consistency2/5

The set uses snake_case everywhere but that is the only consistent part. There is a mess of verb_noun patterns, noun_verb patterns (cjeu_search vs search_legislation, cj_judgment vs get_document), bare noun phrases (entity_profile, compliance_index, pipeworx_feedback, polymarket_edges), and verb phrases (ask_ipeworx, generate_elms_txt, resolve_entry). A user cannot predict whether the noun comes first, so naming is readable but not predictable.

Tool Count2/5

39 tools is far over the 25+ threshold for a coherent set, and a large number of them (predictor markets ten, AI visibility, memory, subscriptions, pipework meta-tools) are outside the EUR-Lex legal research domain. The total count suggests a bundled everything-server rather than a focused legal-research MCP. It is not extreme enough for a 1 because 39 is still within a region where a broader meta-pipework suite could plausibly exist — but it's still too many.

Completeness4/5

For the EUR-Lex domain, the legal tools are nearly complete: search_legislation + compliance_index locate acts, get_metadata/list_articles/get_article/get_document read them, and cjeu_search/cjeu_judgment cover case law. Missing links that would make it fully seamless are amendment tracking, cross-references and direct CELEX/EURL-Lex citation search integration, but all basic 'find and read an act or judgment' workflows are supported.

Resources