Skip to main content
Glama

Hal Fr

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?

Annotations already mark this as read-only, open-world, idempotent, and non-destructive. The description goes beyond these by detailing the return verdicts, the distinction between 'could_not_verify' and 'unsupported', and the important warning that 'could_not_verify' must not be treated as evidence. It also discloses the internal routing logic (SEC EDGAR fast path vs grounded fallback), providing rich behavioral context beyond the 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 well-structured and front-loaded with trigger examples, followed by usage context, return values, and a critical caller warning. Every sentence conveys necessary information: the multi-example opener, the routing behavior, the verdict list, and the could_not_verify caveat. While longer than some tool descriptions, the complexity justifies its length and each sentence earns its place.

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?

Despite lacking an output schema, the description fully characterizes the return values (verdict, grounded/structured value, citation, reasoning) and explains error behaviors (verification_error, unsupported vs could_not_verify). This gives an agent all necessary information to invoke the tool and interpret results correctly, making it contextually complete for a complex verification tool with rich annotations.

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?

Schema coverage is 100% with both parameters (claim, tolerance_pct) described, so the baseline is 3. The description adds extra value by explaining how tolerance_pct overrides the implied wording and its recommended use for hallucination detection (1–2%). It also provides concrete examples of the claim parameter within the description text, reinforcing the schema semantics.

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 states exactly what the tool does: natural-language claim verification against authoritative sources, with clear trigger phrases and examples. It distinguishes itself from siblings by describing its role as a claim verifier (replacing multi-step processes) and its two-path routing (SEC EDGAR fast path vs grounded pipeline), making its purpose unambiguous.

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 gives a clear usage cue: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains the precise behavior for different claim types (financial vs other) and highlights that it replaces 4–6 sequential calls. However, it does not explicitly mention when NOT to use the tool or compare it with alternative tools like ask_pipeworx_grounded or deep_research, so it lacks explicit exclusions.

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

All Hal Fr 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

B3.4/5.0
Disambiguation2/5

Several tools occupy nearly the same role: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are deliberately near-duplicates, while deep_research, validate_claim, bet_research, and the polymarket_* family all route factual questions to overlapping data pipelines. Generic single-word tools like get, search, structure, and author add further ambiguity, making it hard for an agent to confidently pick the right tool.

Naming Consistency3/5

Names are consistently lowercase snake_case, but they mix verb_noun tools (list_subscriptions, resolve_entity, validate_claim) with bare nouns (author, get, search, structure) and domain-prefixed families (ask_pipeworx, polymarket_*, pipeworx_*). The conventions are readable but not predictable enough to infer behavior from the name alone.

Tool Count2/5

35 tools is heavy for a single server, especially when many are meta-routers or near-variants of each other. The broad data-research scope justifies some breadth, but the surface feels padded with overlapping research and prediction-market tools rather than a tight, well-scoped set.

Completeness4/5

For its apparent purpose — authoritative data lookup, verification, research, entity profiling, prediction-market analysis, and monitoring — the surface is largely complete: retrieval, grounded answers, deep research, comparison, change tracking, subscriptions, and memory are all covered. Minor gaps exist, such as no direct tool for managing alert delivery or for some of the vague HAL-style operations, but agents can work around these via the router tools.

Resources