Skip to main content
Glama

Dati It

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

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, and the description adds substantial transparency beyond these: it describes the two distinct execution paths (SEC EDGAR fast path vs. grounded pipeline), the verdict taxonomy, and the critical caveat that 'could_not_verify' must not be treated as evidence. It also discloses the `verification_error` structure and the meaning of 'unsupported', which is valuable behavioral context not present in 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 verbose but every sentence carries essential information — from trigger phrases to routing logic to verdict semantics to the 'replaces 4–6 sequential calls' efficiency statement. It is front-loaded with the most critical use-case indicators. Slightly dense, but not bloated; each clause adds value. A 5 would require even tighter wording, but the content justifies the length.

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 the tool's complexity (two distinct pipelines, multiple verdict categories, error handling, no output schema), the description is remarkably complete. It explains what the tool returns (verdict, actual value, citation, reasoning), what each verdict means, and why 'could_not_verify' is distinct from 'unsupported'. The missing output schema is compensated for by the detailed return-value description. The description fully prepares an agent to use the tool correctly in varied contexts.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds meaning by providing concrete examples for the 'claim' parameter and explaining 'tolerance_pct' semantics (overrides implied tolerance, caps at 5, recommended 1–2 for hallucination detection), which goes beyond the schema's generic 'Max percent deviation' description. The description also ties the parameter behavior to the verdict outcomes, giving context on how the parameter affects results.

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 opens with explicit trigger phrases ('Is it true that…', 'fact check', 'verify the claim that…') and a clear verb+resource: 'natural-language claim verification against authoritative sources.' It distinguishes itself from sibling tools like ask_pipeworx_grounded and deep_research by stating it 'replaces 4–6 sequential calls' and covers both structured and grounded pipelines. The purpose is unambiguous and differentiates from alternatives.

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 states 'Use whenever the agent needs to check whether something a user said is factually correct' and explains the routing logic for company-financial vs. other claims. It also notes that 'could_not_verify' means the check did not happen, clarifying a key edge case. However, it does not explicitly name when NOT to use this tool (e.g., versus deep_research for open-ended research), relying on the 'fact check' framing to imply scope.

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

All Dati It 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

Several tools have overlapping purposes: ask_pipeworx, ask_pipeworx_beta (currently identical), ask_pipeworx_grounded, and deep_research all route to the same 5,529 tools; polymarket_arbitrage and polymarket_edges both find tradeable opportunities; discover_tools and suggest_questions both serve discovery. The beta tool being an exact duplicate makes misselection highly likely.

Naming Consistency3/5

Most action tools follow verb_noun (ask_pipeworx, compare_entities, discover_tools, list_groups, resolve_entity, search_datasets, suggest_questions, validate_claim), but there is significant mixing with noun_noun (dataset_details, entity_profile, organization_details, pipeworx_feedback, polymarket_arbitrage) and adjective_noun (deep_research, recent_alerts). The Polymarket family is consistently prefixed, but overall the server mixes several conventions.

Tool Count2/5

36 tools far exceeds the typically well-scoped range, and the server bundles what appear to be five separate concerns: Italian open data, Pipeworx universal query, entity/report utilities, prediction-market analytics, and meta/memory/subscription features. Many tools could be consolidated (e.g., ai_visibility_check and scan_competitor_ai_presence; discover_tools and suggest_questions), making the set feel bloated.

Completeness4/5

The broad domain of structured data research and prediction-market edge is largely covered: universal routing, grounded answers, deep research, entity resolution, profiles, comparisons, change feeds, claim verification, arbitrage scans, fill-risk, subscriptions, memory, and feedback. Minor gaps exist—no direct tool to fetch raw CKAN resource URLs, no exhaustive list of all 5,529 tools, and no actual order execution on prediction markets—but these are workable around.

Resources