Skip to main content
Glama

Metals Api

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

A4.8/5.0
Behavior5/5

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

Beyond annotations (readOnly, openWorld, idempotent), description discloses the two-pipeline routing, return fields, and crucially distinguishes could_not_verify from unsupported, warning that could_not_verify is not evidence. This is valuable behavioral context not captured in annotations.

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?

Though longer than the benchmark example, every sentence is dense with purpose, usage, return value, and edge-case guidance. It is front-loaded with trigger phrases and the core definition, and the 'IMPORTANT for callers' section is essential.

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 fully specifies the verdict vocabulary, return payload, pipeline selection, error semantics, and efficiency rationale. Since no output schema exists, this is necessary and sufficient for an agent to invoke and interpret results correctly.

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?

Schema already covers both params; description adds meaning: tolerance_pct range, override behavior, default implication (capped at 5), and examples for claim. It also explains the effect on verdict grading, going well beyond the schema 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?

Description opens with trigger phrases, states it is 'natural-language claim verification against authoritative sources,' and names the exact verdict types. It clearly distinguishes from siblings by focusing on fact-checking claims versus general querying.

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?

Explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct' and differentiates between SEC/XBRL fast path for company-financial claims vs grounded pipeline for all other claims. It notes the tool replaces 4–6 sequential calls, but does not name alternative sibling tools for when not to use it.

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

All Metals Api 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

Multiple tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are variants of the same router, and the six polymarket_* tools cover overlapping arbitrage/edge analysis territory. ai_visibility_check vs scan_competitor_ai_presence and discover_tools vs suggest_questions add further boundary ambiguity. While descriptions try to differentiate, an agent could easily misselect among these clusters.

Naming Consistency3/5

Most names are readable snake_case, but there is no consistent verb_noun pattern: verbs vary (ask, get, list, scan, search, suggest, validate, generate, compare) and several tools are named by product prefix (pipeworx_*, polymarket_*) rather than by action. The pattern is predictable within clusters but inconsistent across the set.

Tool Count2/5

33 tools is heavy for the server's stated name, 'Metals Api', which only has two metals-related tools (get_historical, get_latest). Even as a general data-research server, the surface is bloated with memory utilities, subscription management, feedback, trending, and unrelated AI-visibility scanning. The scope mismatch makes the count feel unjustified.

Completeness3/5

The core metals domain is thin: latest and single-date historical prices exist, but there is no time-series range query, no list of supported metals, and no explicit currency conversion endpoint. The broader data-research/subscription/memory surface is relatively complete, but it is disconnected from the server's apparent purpose, leaving notable gaps for a metals-focused agent.

Resources