Skip to main content
Glama

wikifeed

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

A4.7/5.0
Behavior5/5

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

Beyond annotations (read-only, idempotent, etc.), the description discloses crucial behavioral details: the tool can return could_not_verify when the check didn't happen, and that verdict carries verification_error; unsupported means no source was found. It also reveals the internal fallback from structured SEC EDGAR to grounded pipeline. This adds significant context about failure modes and 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 roughly 200 words but is dense with necessary information. It front-loads with natural-language query examples and ends with the critical caveat about could_not_verify. While a bit long, every sentence contributes either to usage guidance, routing logic, return interpretation, or a distinction from alternatives. The structure is clear: what it does, when to use it, how it works, what it returns, and important pitfalls.

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 there is no output schema, the description compensates by listing the possible verdicts and explaining the difference between unsupported and could_not_verify, plus the citation format. It also covers the two processing paths and the tolerance behavior. This makes the description self-sufficient for an agent to know when to call the tool and how to interpret the result.

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

Parameters5/5

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

Although the schema already documents both parameters (claim and tolerance_pct), the description enriches them: it clarifies that tolerance_pct overrides the wording-implied tolerance, recommends 1–2 for hallucination detection, and notes its default cap of 5. This goes beyond the schema's basic property definitions, giving practical guidance for the tolerance parameter.

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 identifies the tool as a natural-language claim verification function with a specific verb ('validate') and resource (factual claims). It provides example queries and distinguishes itself from sibling tools by focusing on truth/false checking, and notes it replaces multiple sequential calls. This makes the purpose unambiguous and differentiates it from general-purpose Q&A tools like ask_pipeworx.

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 states 'Use whenever the agent needs to check whether something a user said is factually correct,' providing a clear trigger condition. It also outlines the two routing paths (company-financial vs other claims), showing when it applies. It does not explicitly name alternatives or when not to use it, but the instruction is strong enough to guide selection.

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

All wikifeed 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
Disambiguation4/5

Most tools have clearly distinct purposes, but some overlap exists: ask_pipeworx and ask_pipeworx_grounded are very similar (one grounded), and multiple Polymarket tools (arbitrage, edges, tracker, fill_risk, kalshi_spread) could be confused despite distinct roles. Overall, an agent can usually differentiate with careful reading.

Naming Consistency3/5

Tool names follow mixed conventions: some use verb_noun (ask_pipeworx, compare_entities), others start with prefixes (pipeworx_, polymarket_, scan_), and a few are nouns (most_read, on_this_day). While readable, there is no consistent pattern, making it harder to predict tool names.

Tool Count3/5

34 tools is high but not extreme for a broad-scope server. However, the server name 'wikifeed' suggests a Wikipedia focus, yet only 4 of 34 tools relate to Wikipedia (featured_article, most_read, on_this_day, picture_of_day). The tool count feels excessive relative to the name, but the actual breadth may justify it.

Completeness4/5

The toolset covers a wide range of domains (company data, prediction markets, factual queries, Wikipedia) with reasonable depth. Minor gaps exist: no Wikipedia search or edit tools, no direct tool for simple web search (relying on ask_pipeworx). Overall, agents can accomplish most tasks without hitting dead ends.

Resources