Skip to main content
Glama

Data Baltimore

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

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses the two-path execution (fast structured vs. grounded fallback), the meaning of each verdict, and the critical caveat that could_not_verify means the check did not happen and must not be treated as evidence. This adds substantial behavioral context not present 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?

The description is long but every sentence adds value: invocation examples, purpose, use case, routing, return format, and warnings. It is well-structured from general to specific, front-loaded with the most actionable info, and avoids redundancy.

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?

For a tool with complex routing, multiple verdicts, and important caveats, the description covers all essential aspects: what it does, when to use it, how it handles different domains, what it returns, and subtle interpretation rules. It also explains the benefit (replacing sequential calls). Nothing critical is missing.

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?

The input schema already achieves 100% coverage of both parameters (claim and tolerance_pct), including detailed descriptions and examples. The tool description does not add new parameter semantics beyond what the schema provides, so the baseline score of 3 is appropriate.

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 that the tool performs natural-language claim verification against authoritative sources, with a specific verb (validate) and resource (claim). It lists example user phrasings and distinguishes from siblings by covering both structured financial and grounded general claims. The purpose is unambiguous and well-differentiated.

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 explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct.' It also clarifies the routing logic (SEC EDGAR for financial, grounded pipeline for other claims) and notes that it replaces a multi-step sequence, giving clear when-to-use guidance. It warns about could_not_verify misuse, providing practical invocation boundaries.

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

All Data Baltimore 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

A4.1/5.0
Disambiguation2/5

Several tool groups overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route questions to the same catalog; entity_profile, recent_changes, and compare_entities cover overlapping company-data territory; ai_visibility_check and scan_competitor_ai_presence are near-duplicates. Agents would frequently need to read long descriptions to pick the right tool.

Naming Consistency4/5

All tool names use snake_case and mostly follow verb_noun patterns (ask_pipeworx, compare_entities, resolve_entity, validate_claim). Minor inconsistencies exist: generic noun-only names like entity_profile, recent_changes, and bet_research, plus inconsistent prefixes (ask_, baltimore_, polymarket_, pipeworx_, scan_) that group by domain rather than action.

Tool Count3/5

34 tools is on the heavy side for a data-access server, though the scope is broad. Several tools feel tangential to the core data mission (remember/recall/forget, generate_llms_txt, pipeworx_feedback, pipeworx_trending), and the ask_pipeworx family plus the six polymarket_* tools inflate the count with overlapping functionality.

Completeness4/5

The surface covers the domain well: discovery (discover_tools, suggest_questions, baltimore_layers), lookup (ask_pipeworx, baltimore_query/recent), grounded verification (ask_pipeworx_grounded, validate_claim), comparison (compare_entities), profiling (entity_profile), change tracking (recent_changes), and prediction-market analysis. Minor gaps include no direct web search and no Baltimore-specific export/bulk operations, but agents can work around these.

Resources