Skip to main content
Glama

Smithsonian

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 annotations (readOnly, idempotent, openWorld, non-destructive), the description reveals important behavioral nuances: the dual-path pipeline (SEC EDGAR/XBRL for financials; grounded pipeline for otherwise), exact percent-delta math, verbatim evidence, and the critical distinction between `could_not_verify` (check did not happen) and `unsupported` (no source coverage). It also warns that `could_not_verify` must not be presented as evidence for or against the claim.

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 front-loaded with purpose and usage, then details routing, return values, and caller caveats. Each sentence adds value; the structure is logical. Slightly verbose due to trigger-phrase examples and the 'Replaces 4–6 calls' benefit, but not wasteful.

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 no output schema, the description fully enumerates the verdict types and conveys the actual value, citation, and reasoning. It covers edge cases (`could_not_verify`, `unsupported`) and instructs callers on how to handle them. It also explains the two internal pipelines, making the tool's behavior predictable across claim categories.

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

Parameters3/5

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

Schema coverage is 100% and both parameters are already well-documented in the input schema (claim examples, tolerance_pct with override behavior and default). The description restates some of these details (e.g., percent-delta math) but adds little beyond schema semantics. Baseline 3 applies for high schema coverage.

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 opens with natural-language trigger phrases ('fact check', 'verify the claim that…') and clearly states the tool performs 'natural-language claim verification against authoritative sources.' It differentiates from sibling research/search tools by emphasizing it returns a verdict and handles two distinct claim categories (company-financial vs. other factual claims).

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?

Explicitly states 'Use whenever the agent needs to check whether something a user said is factually correct.' It also describes the fallback routing for non-financial claims and notes that `could_not_verify` vs `unsupported` have distinct meanings, guiding the caller's interpretation. Bonus: it mentions replacing 4–6 sequential calls, clarifying when the tool is a better single-call alternative.

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

All Smithsonian 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
Disambiguation3/5

Many tools serve overlapping purposes, such as the three ask_pipeworx variants (stable, beta, grounded) and the six Polymarket-specific tools. While detailed descriptions help distinguish them, an agent could still confuse bet_research with polymarket_edges or the ask_pipeworx versions.

Naming Consistency2/5

Naming is highly inconsistent: verb_noun (ask_pipeworx, compare_entities), noun_noun (bet_research, entity_profile), single verbs (forget, recall, search), and adjective_noun (recent_alerts, deep_research). No clear pattern emerges across the set.

Tool Count3/5

33 tools is on the high side for a server named 'Smithsonian' that actually covers a broad range of data sources (SEC, FDA, Polymarket, npm, etc.). The number feels borderline heavy but is still manageable if the server's true purpose is general research.

Completeness4/5

The tool set covers multiple domains (company financials, drugs, economics, prediction markets, npm, museum data) with reasonable depth. Minor gaps exist, such as lack of PyPI scanning or missing update/delete operations for some memory features, but core workflows are well-supported.

Resources