Skip to main content
Glama

NS Pros MCP Gateway

ntsb-investigations__validate_claim

"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 sta

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "claim": "Apple's fiscal 2023 revenue was $383 billion"
    },
    "name": "ntsb-investigations__validate_claim"
  }
}

Input 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.

  1. First observed

TDQS

B3/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose real behavioral traits: exact percent-delta math for financial claims, a fast path vs. a slower path, and a grading vocabulary ('approximately_correct') with tolerance overridable. It says nothing about source coverage limits, failure modes, or what happens when no authoritative source is found, and the disclosure is cut off mid-word.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening is a long slash-delimited string of quoted trigger phrases that is front-loaded but bloated, and the final sentence terminates mid-word ('macro sta'), leaving the definition visibly incomplete. The most decision-relevant fact — which source domain this tool covers — is absent from what survives.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description must explain both behavior and return semantics; it hints at grading labels but never enumerates the possible verdicts or their meanings. Combined with the truncation and the missing identification of the NTSB source corpus, an agent lacks what it needs to decide between this tool and any of its many identically named siblings.

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 description coverage is 100%, so `claim` and `tolerance_pct` are already fully documented, establishing a baseline of 3. The description adds a little: it clarifies that tolerance is normally implied by claim wording (matching the schema's 'Default: implied by wording'), but it does not elaborate on grading thresholds or how `tolerance_pct` interacts with the percent-delta math beyond what the schema already says.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description does name a specific verb+resource (natural-language claim verification against authoritative sources) and adds a routing distinction for company-financial claims via SEC EDGAR/XBRL. However, it never identifies the tool's own source domain (NTSB investigations), which is the only thing distinguishing it from dozens of sibling tools all named `validate_claim`. An agent cannot tell from this text which source corpus backs the 'ANY OTHER factual claim' path.

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?

Trigger phrases are enumerated explicitly ("Is it true that...", "fact check", "confirm or refute") and the description states 'Use whenever the agent needs to check whether something a user said is factually correct'. It also sketches routing: company-financial claims go through the SEC EDGAR fast path. Missing is any exclusion or named alternative for claims outside this tool's domain, which is left to the truncated sentence.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.