Skip to main content
Glama

Digitalnz

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

A4.6/5.0
Behavior5/5

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

Even with annotations (readOnly, openWorld, idempotent), the description adds substantial behavioral context: it explains the automated routing (fast path for SEC financials vs. grounded pipeline), defines each verdict meaning, crucially warns that 'could_not_verify' means the check did not happen and must not be treated as evidence, and clarifies the 'unsupported' semantic. It also reveals the internal error structure (verification_error with stage/detail), which is not inferable from annotations.

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 dense but each section earns its place: trigger phrases, use cases, pipeline differentiation, verdict semantics, caveats, and efficiency gains. It is somewhat long, but the complexity of the tool justifies the length. Front-loaded with example phrases makes it immediately scannable. A slight redundancy exists between the phrase list and the rest, but it does not detract significantly.

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?

This is a complex tool with two execution paths, multiple possible verdicts, and important error semantics, yet no output schema. The description covers all of these: what inputs are expected, how each claim type is processed, what return values look like (verdict, value, citation, reasoning), and the crucial distinction between 'could_not_verify', 'unsupported', and 'refuted'. It is complete enough for an agent to select and invoke the tool correctly without further documentation.

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 baseline is 3. The description adds meaningful nuance beyond the schema: it explains that 'tolerance_pct' overrides the claim's implied tolerance, gives a practical range (1-2) for hallucination detection, and states the default behavior (implied by wording, capped at 5). It also provides example claims for the 'claim' parameter, reinforcing the natural-language format.

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's function: natural-language claim verification against authoritative sources, with specific verb ('verify') and resource (factual claims). It distinguishes itself by detailing two distinct pipelines (SEC EDGAR structured path and grounded fallback) and explicitly lists the output verdict types, making it unmistakable what the tool does. This is significantly more specific than a generic 'validates claims' statement.

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.' It also provides conditional guidance based on claim type (company-financial vs. other) and notes that it replaces 4-6 sequential calls, implying you should use this tool rather than orchestrating multiple steps. However, it does not explicitly name alternative tools or state when *not* to use it, missing a full exclusion clause.

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

All Digitalnz 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

A3.7/5.0
Disambiguation2/5

The tool set contains multiple clusters with heavy overlap: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route questions to the same underlying data sources, making it ambiguous which to choose. Similarly, polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, and bet_research all target prediction-market opportunities with fuzzy boundaries between them. The three DigitalNZ tools (search, record, search_within) are distinct, but the rest of the set obscures their purpose.

Naming Consistency3/5

Most tools use snake_case with descriptive names, and the polymarket_* cluster is consistent among itself. However, conventions are mixed: some are verb-first (validate_claim, discover_tools, remember), some are noun-first (entity_profile, recent_changes), and ask_pipeworx_beta breaks the pattern with a suffix variant. The naming is readable overall but not uniform.

Tool Count2/5

At 33 tools, the server exceeds the 25-tool threshold for a 'too heavy' count. The vast majority of tools belong to the Pipeworx data-query and prediction-market domains rather than DigitalNZ, which is the server's stated name. A focused DigitalNZ server would need closer to 5-10 tools; a Pipeworx server would still be over-packed at 33 given the functional overlap.

Completeness2/5

For the DigitalNZ domain, the surface is severely incomplete: only search, record, and search_within exist, with no browse, filter, facet, or contribution capabilities. The Pipeworx side is more complete but still has gaps (e.g., no direct per-source query tools, and several tools soft-fail on sunset APIs). The server tries to cover two unrelated domains and satisfies neither fully.

Resources