Skip to main content
Glama

Data Oakland

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

A4.4/5.0
Behavior5/5

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

The description adds rich behavioral context that annotations do not cover: it explains the meaning of 'could_not_verify' (system failure, not evidence) versus 'unsupported' (no source), reveals the internal routing logic (SEC EDGAR vs grounded pipeline), and notes the response includes a citation and reasoning. This goes well beyond the readOnly/openWorld/idempotent hints and provides critical guidance for interpreting results.

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 a typical one-liner but every sentence contributes useful information: purpose, routing, return format, and critical caveats. It is well-structured, starting with the core purpose and then elaborating on behaviors. It is not excessively verbose for the tool's complexity, though it could be tightened by removing the call-count comparison ('Replaces 4–6 sequential calls') which is more of a benefit than a semantic detail.

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 covers all necessary aspects: what the tool does, how it routes different claim types, what it returns (verdict list, actual value, citation, reasoning), and how to interpret ambiguous outcomes ('could_not_verify' vs 'unsupported'). Although there is no output schema, the description explicitly lists the possible verdict values and the error field, providing sufficient completeness for an agent to invoke and handle results correctly.

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 'claim' and 'tolerance_pct' already have detailed descriptions in the input schema, including defaults and usage examples. The tool description does not add any additional parameter-specific meaning beyond what the schema provides (e.g., no extra detail on claim format or tolerance behavior beyond the schema's own text). Therefore, the description adds no incremental value for parameters, and a 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 the tool performs 'natural-language claim verification against authoritative sources,' with a specific verb ('verify') and resource ('claims'). It distinguishes itself from siblings by describing a fast path for company-financial claims and a grounded pipeline for other claims, which is more specific than general purpose tools like ask_pipeworx or deep_research.

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 says 'Use whenever the agent needs to check whether something a user said is factually correct,' giving a clear when-to-use directive. It also explains the routing behavior for different claim types and mentions it replaces 4–6 sequential calls, implying it should be used instead of chaining other tools. However, it does not explicitly name alternative tools or provide when-not-to-use conditions, so it doesn't fully meet the 'vs alternatives' bar.

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

All Data Oakland 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

Several tool clusters have unclear boundaries: ask_pipeworx and ask_pipeworx_beta are explicitly identical today, with ask_pipeworx_grounded and deep_research routing through the same 5,756-tool catalog, and validate_claim falling into the same grounded pipeline. The five polymarket_* tools plus bet_research all target prediction-market opportunities with overlapping outputs (edge_pp vs gap_pp vs spread_pp), and compare_entities/entity_profile/recent_changes share the same SEC/XBRL/news fan-out. The verbose descriptions help, but the set itself would frequently misroute an agent.

Naming Consistency3/5

All names are uniformly snake_case with no casing mixing, and the ask_pipeworx_*, polymarket_*, and pipeworx_* prefixes create recognizable families. However, the set mixes verb_noun names (validate_claim, list_subscriptions), bare verbs (query, recall, forget), and noun-phrase names (entity_profile, recent_alerts, datasets, metadata), so there is no single predictable pattern across the server.

Tool Count3/5

34 tools is heavy, but the server's scope is genuinely enormous: it is a gateway to 5,756 tools across 1,504 sources, plus prediction-market analysis, subscriptions, and memory. The count is defensible for that scope, yet several tools (generate_llms_txt, scan_dependency, ai_visibility_check, the memory trio) are peripheral to the core data mission, giving the set a scattershot feel and preventing a well-scoped rating.

Completeness4/5

The core data-research workflow is thoroughly covered: casual lookup (ask_pipeworx), grounded verification (ask_pipeworx_grounded, validate_claim), deep research (deep_research), entity resolution and profiling (resolve_entity, entity_profile, compare_entities, recent_changes), and a six-tool prediction-market suite. Subscriptions and memory have full lifecycles, and Oakland data offers search, schema, and query. Minor gaps exist — no subscription update/pause, no raw dataset export, and no write path for Oakland data — but no advertised workflow hits a dead end.

Resources