Skip to main content
Glama

Markdown

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 indicate read-only, open-world, idempotent, and non-destructive behavior. The description significantly enriches this by explaining the two verification paths (structured vs. grounded), enumerating all verdict types, and crucially distinguishing 'could_not_verify' (claim not checked, not evidence) from 'unsupported' (no source covers it). It also warns callers not to treat 'could_not_verify' as evidence for or against. No contradictions with 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 dense and front-loaded with examples and core purpose, immediately clarifying what the tool does. Every sentence earns its place—routing, return format, and error semantics are all covered without redundancy. It is longer than a minimal description, but given the tool's complexity (two execution paths, verdict nuance), it is appropriately sized and well-structured.

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 it does so thoroughly: it lists all possible verdicts, describes the citation format, explains the meaning of 'could_not_verify' and 'unsupported,' and details the two execution paths. It also notes the tool's efficiency advantage over sequential calls. This is near-complete for safe and correct invocation.

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 input schema already documents both parameters (claim with examples, tolerance_pct with range and purpose) at 100% coverage. The description adds valuable context beyond the schema: tolerance_pct overrides the tolerance implied by the claim wording, can be set to 1–2 for hallucination detection, and defaults to a cap of 5. This goes beyond the schema's baseline, so a 4 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 explicitly states the tool performs natural-language claim verification against authoritative sources, with concrete trigger phrases ('fact check,' 'verify the claim that…') and a clear goal: checking factual correctness of user statements. It distinguishes itself from siblings by describing the verdict output and the fact it replaces a 4–6 step sequential pipeline.

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 explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct' and provides routing context (company-financial claims use SEC EDGAR/XBRL, other claims fall through to a grounded pipeline). However, it does not name alternative tools for non-verification tasks or explicitly state when not to use it, so it misses the 'when-not/alternatives' bar for a 5.

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

All Markdown 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 tool clusters are hard to distinguish: the four ask_pipeworx variants overlap heavily (beta currently behaves identically to ask_pipeworx, and grounded shares routing), and the half-dozen prediction-market tools (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) have fuzzy boundaries. Memory and markdown utilities are clear, but the overlapping data-query and prediction-market clusters create real misselection risk.

Naming Consistency4/5

Names are almost uniformly snake_case and mostly verb-first (ask_, compare_, extract_, scan_, validate_, remember, forget), which is predictable. Minor deviations like entity_profile, recent_changes, and polymarket_edges are noun-first but still follow the same lowercase_snake pattern, so no chaotic mixing of conventions exists.

Tool Count2/5

34 tools is heavy for a server seemingly named 'Markdown', especially when the majority are actually Pipeworx data-research and prediction-market tools. Several tools duplicate or wrap each other (ask_pipeworx_beta, scan_competitor_ai_presence, bet_research et al.), so the count feels bloated; it is not as extreme as 50+, but it exceeds a well-scoped set.

Completeness4/5

Within the actual dominant domain — structured data research plus prediction markets — the surface is broad: routing queries, grounded answers, deep research, entity profiles, comparisons, resolution, claim validation, semantic search, discoverability, subscriptions/alerts, and memory are all covered. Minor gaps exist (e.g. no direct pipeworx:// citation-fetch tool, and markdown support is thin), but the core workflows have no dead ends.

Resources