Skip to main content
Glama

dictionary

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. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnly/idempotent hints, the description reveals critical behavior: the distinction between 'could_not_verify' (the check did not happen) and 'unsupported' (no source exists), the existence of verification_error{stage,detail}, and the fact that could_not_verify must not be shown as evidence. It also details the return structure with verdict, grounded/structured value, and citation, which is essential for correct agent interpretation.

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 and front-loaded with user intents and the primary action. While lengthy, each sentence contributes meaningful information: routing logic, verdict semantics, and efficiency benefit. It could be slightly more concise, but the structure supports a complex, multi-behavior tool.

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 carries the full burden of explaining return values and edge cases. It thoroughly covers the verdict list, the actual value with citation, reasoning, and the special meanings of 'could_not_verify' and 'unsupported'. It also explains internal routing and failure modes, making it fully complete for a 2-parameter tool.

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?

The schema already provides full descriptions for both parameters (100% coverage). The description adds behavioral nuance by mentioning 'exact percent-delta math' and how tolerance_pct overrides the wording-implied tolerance, clarifying usage for hallucination detection. It also gives real-world examples of claim syntax, enriching understanding beyond the schema.

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 provides concrete example intents like 'fact check' and 'verify the claim that…', and specifies the scope (company-financial vs any other claim). It distinguishes itself from generic research tools by explicitly noting it 'Replaces 4–6 sequential calls', making it a unique composite verifier.

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 guidance: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also separates the fast path for company-financial claims from the fallback grounded pipeline. However, it does not name alternative sibling tools or provide explicit 'when-not to use' rules, though it implies it replaces multi-step research.

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

All dictionary 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

A3.9/5.0
Disambiguation2/5

Several tools have near-identical purposes: ask_pipeworx, ask_pipeworx_beta (explicitly identical today), and ask_pipeworx_grounded are the same router with only an evidence-extraction difference. polymarket_edges, bet_research, and polymarket_arbitrage also overlap heavily in surfacing mispricings, and ai_visibility_check is essentially a single-entity version of scan_competitor_ai_presence.

Naming Consistency3/5

There are recognizable patterns: ask_pipeworx_*, polymarket_*, verb_noun pairs like define_word, get_synonyms, resolve_entity. However, conventions are mixed across the set — ask_pipeworx_beta uses a suffix, ai_visibility_check vs scan_competitor_ai_presence are phrased in different styles, and memory tools (remember/recall/forget) follow yet another pattern. Readable but not predictable.

Tool Count2/5

33 tools is heavy for a single server, and many of them are meta-tools (discover_tools, suggest_questions, ask_pipeworx variants, pipeworx_trending, pipeworx_feedback, memory tools) that inflate the surface. The count would be defensible if each tool were orthogonal, but the overlap in research/Polymarket/memory areas means several tools do not earn their place.

Completeness4/5

For the actual Pipeworx data-access domain, coverage is quite rich: lookup, grounded answers, deep research, entity profiles, comparisons, claim validation, subscriptions, memory, and discovery tools all exist. Minor gaps remain (e.g., no tool to manage account/API keys, patents soft-fail), but the core query-research-monitor lifecycle is well covered. The server name 'dictionary' is misleading — only two tools serve a dictionary purpose — yet the inferred domain from descriptions is a data gateway, for which the surface is strong.

Resources