Skip to main content
Glama

Data Sncf

by io.github.pipeworx-io

Validate Claim

validate_claim
Read-onlyIdempotent

"Is it true that…" / "fact check" / "verify the claim that…" / "did X really…" / "was Y actually…" / "confirm or refute" / "true or false" — natural-language claim verification against authoritative sources. Use whenever the agent needs to check whether something a user said is factually correct. Company-financial claims (revenue, net income, cash for public US companies) verify via the structured SEC EDGAR + XBRL fast path with exact percent-delta math; ANY OTHER factual claim (macro statistics, rates, prices, drug data, records) automatically falls through to the grounded pipeline — routed to the right live source, answered with verbatim evidence, then judged. Returns a verdict (confirmed / approximately_correct / refuted / inconclusive / unsupported / could_not_verify), the grounded or structured actual value with pipeworx:// citation, and reasoning. IMPORTANT for callers: could_not_verify means the check did not happen (our LLM or source failed) and carries verification_error{stage,detail} — it is NOT evidence for or against the claim, and must not be shown as one. unsupported means we looked and cover no source for it. Replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → comparison).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
claimYesNatural-language factual claim, e.g., "Apple's FY2024 revenue was $400 billion" or "Microsoft made about $100B in profit last year".
tolerance_pctNoMax percent deviation still graded approximately_correct (0.5–50). Overrides the tolerance implied by the claim wording — set 1–2 for hallucination detection where any material error must be refuted. Default: implied by wording, capped at 5.

Schema Changelog

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

  1. Changed1 schema field changed
    • addedInput schema / properties / tolerance_pct
      Added value: +{
+  "description": "Max percent deviation still graded approximately_correct (0.5–50). Overrides the tolerance implied by the claim wording — set 1–2 for hallucination detection where any material error must be refuted. Default: implied by wording, capped at 5.",
+  "type": "number"
+}
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, and non-destructive behavior, and the description adds significant behavioral context: internal pipeline (SEC EDGAR + XBRL fast path, grounded fallback), verdict types, and the crucial clarification that could_not_verify means the check did not happen and must not be treated as evidence. This is valuable beyond the annotations.

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 long but front-loaded with purpose and query phrasings. Each sentence carries meaningful operational information (pipeline steps, verdict semantics, caller warning, efficiency comparison). It could arguably be tightened, but the length is justified by the tool's complexity and there is no filler. Structure is logical and clear.

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?

With no output schema, the description fully specifies the return structure (verdicts, actual value with citation, reasoning) and elaborates on edge cases (could_not_verify with verification_error, unsupported). Combined with the rich parameter schema and annotations (read-only, idempotent), the description leaves no major operational gap for an agent 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?

Schema coverage is 100%: both claim and tolerance_pct have detailed descriptions with examples and defaults. The tool description does not add parameter-specific meaning beyond the schema; it mentions 'exact percent-delta math' in passing but that is more behavioral than parameter guidance. Baseline 3 is appropriate due to high schema coverage.

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: natural-language claim verification against authoritative sources. It lists specific query phrasings ('Is it true that...', 'fact check', 'verify the claim that...') and explicitly says to use it when checking if something a user said is factually correct. It also distinguishes itself from siblings by noting it replaces 4–6 sequential calls and handles two distinct pathways (structured SEC EDGAR vs grounded fallback), making it uniquely suited for fact-checking.

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

Usage Guidelines4/5

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

The description gives explicit context: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also details the two scenarios (company-financial claims via SEC EDGAR, any other claim via grounded pipeline). However, it does not explicitly name alternative tools or state when not to use it, so it falls short of a 5.

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

All Data Sncf 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

A3.6/5.0
Disambiguation2/5

Several tool clusters are hard to distinguish: ask_pipeworx_beta explicitly states it 'currently matches ask_pipeworx exactly', creating a literal duplicate, and the six polymarket_* tools all orbit 'find a trading edge on prediction markets' with only subtle differences in scope. ask_pipeworx / ask_pipeworx_grounded / validate_claim / deep_research also overlap on fact-finding, and discover_tools vs suggest_questions both serve 'what can I do here' discovery. The memory trio and subscription lifecycle are clean, but the central Q&A and prediction-market areas carry real misselection risk.

Naming Consistency2/5

The set mixes several incompatible conventions: bare verbs (query, recall, forget, remember), noun phrases (entity_profile, dataset_info), verb_noun pairs (search_datasets, compare_entities, validate_claim), and prefixed families (polymarket_*, ask_pipeworx_*, pipeworx_*). Family prefixes provide local consistency, but there is no unifying pattern across the server, and the three SNCF tools follow a different style from the Pipeworx tools. The naming reads as several mini-servers bolted together rather than one coherent API.

Tool Count2/5

At 34 tools, the count exceeds the comfortable range and is inflated by genuine redundancy: ask_pipeworx_beta duplicates ask_pipeworx, ask_pipeworx_grounded is a paid variant, scan_competitor_ai_presence wraps ai_visibility_check, and six Polymarket tools could plausibly be consolidated. The server name promises a narrow SNCF data scope, yet 31 of 34 tools serve an unrelated universal data / prediction-market platform, making the count feel both bloated and mismatched to the server's stated identity.

Completeness3/5

For the dominant inferred domain (Pipeworx structured-data Q&A, research, and prediction markets), the surface is quite complete: discovery, routing, grounded answers, deep research, claim verification, entity resolution, profiles, comparisons, change feeds, subscriptions, and memory are all present. However, relative to the server's stated name 'Data Sncf', the SNCF surface is minimal (search -> metadata -> query) with no update feeds, record-level fetch, or live railway status, and the two domains never connect. The orphaned single-purpose tools (generate_llms_txt, scan_dependency) further fragment the sense of a coherent domain.

Resources