Skip to main content
Glama

Oecd

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. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses critical behavioral details: the automatic routing between structured and grounded pipelines, the meaning of each verdict, and the crucial warning that 'could_not_verify' means the check did not happen and must not be treated as evidence. This is valuable context that annotations alone do not provide. No contradiction with 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?

Although the description is long, every sentence adds necessary information. It is front-loaded with the query forms and core purpose, then systematically covers pipelines, return values, and error semantics. The structure is logical with distinct paragraphs for purpose, behavior, and warnings — nothing is redundant or extraneous.

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?

With only 2 parameters and no output schema, the description compensates by fully explaining the return values (verdict types, citation, reasoning), the meaning of 'could_not_verify' vs. 'unsupported', and the two execution paths. It also ties into the broader workflow by noting it replaces multiple sequential calls. The tool is fully specified.

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

Parameters4/5

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

The input schema already provides 100% coverage with clear descriptions for both parameters. The description adds extra value by explaining the purpose of 'tolerance_pct' (overrides implied tolerance, set 1–2 for hallucination detection) and gives representative claim examples. This goes beyond the schema's basic 'max percent deviation' definition.

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 a specific verb+resource: 'natural-language claim verification against authoritative sources.' It also provides concrete natural-language triggers ("Is it true that…" / "fact check") and distinguishes itself from siblings by focusing on verifying factual claims rather than searching or researching broadly. The two-path explanation (SEC/XBRL fast path vs. grounded pipeline) adds further precision.

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?

It explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct,' which is clear. It also differentiates between company-financial claims and any other claims, giving specific guidance on what to expect in each case. However, it doesn't name sibling alternatives for when to *not* use this tool, though the 'Replaces 4–6 sequential calls' comment implies it's a consolidated replacement.

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

All Oecd 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

Several near-duplicate lookup and prediction-market tools make selection ambiguous: ask_pipeworx_beta deliberately mirrors ask_pipeworx, and the five polymarket_* tools plus bet_research all target the same general 'should I bet / where is the edge' use case. The descriptions are detailed, but at the set level an agent must read extensive disambiguation essays to avoid picking the wrong tool.

Naming Consistency3/5

The set is uniformly snake_case, and subfamilies like ask_pipeworx*, polymarket_*, and subscribe/unsubscribe are internally consistent. However, conventions vary widely: verb_noun (fetch_dataset, validate_claim), noun phrases (entity_profile, bet_research), bare verbs (remember, recall, forget), and prefix-branded meta tools (pipeworx_feedback, pipeworx_trending) all coexist without a single predictable pattern.

Tool Count2/5

34 tools for a server nominally called 'Oecd' vastly exceeds the scope implied by the name and crosses the 25+ too-many threshold. Many tools belong to unrelated domains such as Polymarket arbitrage, npm dependency scanning, llms.txt generation, and AI visibility audits, making the set feel like a broad dumping ground rather than a focused tool server.

Completeness4/5

Within its sprawling domains the tool surface is fairly complete: lookup, grounded verification, deep research, entity resolution/profile/comparison, memory, subscriptions, alerts, and OECD dataflow search/list/fetch are all represented. There are minor gaps such as lack of direct OECD metadata descriptions or deeper navigation of the 5,708 underlying tools, but most workflows can be completed without dead ends.

Resources