Skip to main content
Glama

Pub Dev

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?

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses critical behavioral details: the two routing paths, verdict semantics including the definitive caveat that 'could_not_verify means the check did not happen' and 'must not be shown as evidence', and the unsupported verdict meaning no source coverage. It also explains error handling via verification_error{stage,detail} and the percent-delta math. No contradiction 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 longer than average but well-structured, front-loaded with natural-language trigger phrases. Each section serves a purpose: examples, routing, verdicts, and error warnings. There is minor redundancy (e.g., 'natural-language' appears multiple times) but no wasted sentences. It might be slightly dense but remains focused and scannable.

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 explains the return values: the six verdicts, the actual value with pipeworx:// citation, and reasoning. It also covers failure modes (verification_error) and the difference between could_not_verify and unsupported. This is a complete picture for a tool with two simple parameters and no nested objects, making it easy for an agent to interpret results correctly.

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 covers both parameters with descriptions and examples, so the baseline is 3. The description adds extra value by explaining that tolerance_pct overrides the tolerance implied by the claim wording and gives a specific use case ('set 1–2 for hallucination detection'). This goes beyond the schema's stated range and default.

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, with examples of trigger phrases. It distinguishes itself from generic search tools by describing specialized routing (SEC EDGAR fast path for company-financial claims, grounded pipeline for other facts) and a categorized verdict output. This is a specific verb+resource combination, not a tautology.

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 to 'Use whenever the agent needs to check whether something a user said is factually correct' and provides trigger phrase examples. It also differentiates between claim types (company-financial vs. other) and notes it replaces 4–6 sequential calls. However, it does not name sibling tools or explicit exclusions, so it stops short of a full when-not-to-use list.

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

All Pub Dev 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

A4/5.0
Disambiguation3/5

Several tools have clear functional boundaries, but there is meaningful overlap at the top level: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded share one routing pipeline, and ask_pipeworx_beta is currently identical to ask_pipeworx. The six polymarket_* tools also form a dense family where an agent must read long descriptions to distinguish arbitrage scanning from edge detection from fill-risk evaluation.

Naming Consistency4/5

Names are uniformly lowercase snake_case and mostly follow verb_noun or domain-prefix conventions, which makes the set much more predictable than its count suggests. Minor deviations exist: ask_pipeworx variants are product-noun phrases, polymarket_edges is a noun phrase rather than a verb-led tool, and pairs like polymarket_edges vs polymarket_edge_tracker are easy to misread.

Tool Count2/5

With 31 tools, this server is above the 25+ threshold and feels overloaded for a single MCP surface. It mixes broad data research, prediction-market analysis, memory, subscriptions, feedback, and niche utilities like generate_llms_txt, so the set is more like several related servers merged together.

Completeness4/5

The core workflow is well covered: discovery, single-answer routing, grounded verification, deep research, entity resolution, comparison, change tracking, subscription lifecycle, and even memory primitives. Missing are minor lifecycle refinements such as updating an existing subscription, and the number of overlapping entry points makes it slightly harder to guarantee the agent will always choose the intended path.

Resources