Skip to main content
Glama

Ecb

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

A5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds substantial behavioral context beyond these: it explains the fast path vs. grounded pipeline, details the verdict values, describes the failure mode 'could_not_verify' as 'NOT evidence for or against the claim', and clarifies 'unsupported' semantics. It also reveals the efficiency benefit (replaces 4–6 calls). This goes considerably beyond the annotations and is consistent with them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence earns its place. It opens with concrete query examples to anchor the input format, then briefly explains the dual pipeline, lists return values, and delivers critical caller guidance about error semantics. The structure is logical and front-loaded, and the length is proportional to the tool's complexity. No filler or redundant repetition of schema/annotations.

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?

The description is fully complete for a tool of this complexity. It explains the two routing paths, the verdicts, the citation format, the handling of edge cases (could_not_verify vs. unsupported), and the efficiency gain. Since there is no output schema, the description's explanation of the return structure is essential and sufficient. It leaves no critical behavioral question unanswered.

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?

Even though schema coverage is 100%, the description adds meaningful semantics beyond the schema. For 'claim', it gives natural-language examples and emphasizes the 'natural-language factual claim' format. For 'tolerance_pct', it explains the default behavior ('implied by wording, capped at 5'), how to override it, and provides a specific recommendation (set 1–2 for hallucination detection). This helps the agent select and populate parameters correctly beyond the schema's basic descriptions.

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: verifying natural-language factual claims against authoritative sources. It provides multiple example phrasings ('fact check', 'verify the claim that…'), explicitly mentions the return verdict types, and distinguishes itself from siblings by noting it replaces 4–6 sequential calls. The verb 'verify' and resource 'claims' are specific, and it differentiates from other tools like ask_pipeworx_grounded by focusing on claim verification rather than general queries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage guidance: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also specifies two distinct routing paths (company-financial claims via SEC EDGAR fast path, all other claims via the grounded pipeline), which tells the agent exactly when this tool is appropriate. It further implies that for non-fact-checking queries, other tools like ask_pipeworx should be used, providing effective context for tool selection.

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

All Ecb 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

There is significant overlap between tool clusters: ask_pipeworx_beta is currently functionally identical to ask_pipeworx, and polymarket_arbitrage/polymarket_edges/bet_research all target similar opportunity-discovery tasks. While the descriptions are extremely detailed, the sheer number of similar variants makes it hard to reliably pick the right one.

Naming Consistency4/5

Names are consistently snake_case with meaningful prefixes (ask_, ecb_, polymarket_, pipeworx_) and mostly verb-first structure. Minor deviations like entity_profile and ecb_hicp_inflation are noun-first, but they do not break the overall pattern.

Tool Count2/5

35 tools is well beyond the well-scoped 3–15 range, and the surface feels bloated with redundant meta-tools (ask_pipeworx variants, deep_research, discover_tools, suggest_questions) and peripheral utilities like generate_llms_txt and scan_dependency. Many entries could be consolidated without losing function.

Completeness4/5

For the server's broad data-research domain, coverage is thoughtful and full: query, grounded answer, validation, entity resolution, profiling, comparative analysis, subscription lifecycle, memory, and feedback are all represented. Minor gaps exist (e.g., no direct raw ECB flow browser beyond generic SDMX) but nothing blocking.

Resources