Skip to main content
Glama

Confluence

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

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive. The description adds critical behavioral semantics: the distinction between could_not_verify (check did not happen, must not be used as evidence) and unsupported (no source), the verdict set, and the pipeline routing (SEC EDGAR + XBRL with exact math vs grounded pipeline). This goes far beyond annotation and prevents dangerous misuse.

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 long but front-loaded: it begins with purpose and trigger examples, then dives into routing, output, and a high-importance caller warning before ending with an efficiency note. Every section adds necessary information; the formatting with line breaks and 'IMPORTANT for callers' helps scanning. Though verbose, the complexity of the tool justifies the length.

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 the tool has no output schema, the description must explain return values—it does, listing the possible verdicts, the inclusion of a grounded/structured actual value with citation, and reasoning. It also covers error semantics (verification_error with stage/detail) and what unsupported means. The main gap is lack of explicit instructions on when not to use (e.g., subjective questions), but for a claim-verification tool the core cases are covered.

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%, so the structural meaning is already documented. The description enriches tolerance_pct with tactical guidance ('set 1–2 for hallucination detection where any material error must be refuted') and explains how default tolerance is implied by wording and capped at 5. It also gives concrete examples of claim input, adding practical semantics beyond schema.

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 and explicitly states 'natural-language claim verification against authoritative sources,' clearly distinguishing it from sibling QA tools by naming the verdict output and the two processing paths (SEC EDGAR fast path vs grounded pipeline). This gives a specific verb+resource with strong differentiation.

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 says 'Use whenever the agent needs to check whether something a user said is factually correct,' giving an explicit usage context. It also explains the two routing branches and notes that it replaces 4–6 sequential calls, implying efficiency vs alternative multi-step approaches. It does not name specific sibling tools, so it lacks explicit exclusions, but the guidance is clear.

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

All Confluence 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

The set is dominated by near-overlapping research tools: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all answer factual questions with heavily overlapping descriptions, and the six polymarket_* tools plus bet_research form a second confused cluster. The five confluence_* tools are distinct, but an agent would struggle to pick among the research/betting alternatives without reading thousands of words of caveats.

Naming Consistency2/5

Most names are snake_case, but the conventions are mixed: verb_noun (confluence_create_page, validate_claim), noun_verb (bet_research), prefixed nouns (polymarket_arbitrage, pipeworx_feedback), and bare verbs (recall, forget). The glaring issue is that the server is named Confluence yet only 5 of 36 tools carry the confluence_ prefix, leaving the other 31 tools with no thematic prefix and no consistent pattern.

Tool Count2/5

36 tools is already in the 'too many' range, but the mismatch is deeper: only 5 tools relate to Confluence while 31 tools cover an entirely different domain (Pipeworx data research, prediction markets, subscriptions). For a wiki server this is wildly over-scoped; as a combined surface it is bloated and lacks a unifying purpose.

Completeness2/5

For the Confluence domain the surface is incomplete: pages can be created, fetched, listed, and searched, but there is no update_page, delete_page, comment, attachment, or content-type coverage, leaving obvious CRUD dead ends. For the Pipeworx domain, coverage is broad but disorganized, with overlapping research paths and no clear hierarchy.

Resources