Skip to main content
Glama

Phishtank

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

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, but the description goes far beyond them by explaining the two routing paths, the exact percent-delta math, and the return verdict list. Critically, it discloses the nuanced meaning of 'could_not_verify' (the check did not happen, not evidence) vs 'unsupported' (no source exists), which is essential for correct interpretation. This is exceptional behavioral disclosure.

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 relatively long (about 150 words) but every part contributes: examples for purpose clarity, routing logic, return values, and the error distinction. It is front-loaded with 'Use whenever' and the main purpose, then dives into mechanics. While it could be trimmed (e.g., the example phrasings are a bit redundant), the length is justified by the tool's complexity.

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 no output schema, the description must explain return values, and it does thoroughly: it lists the six verdicts, mentions the grounded/structured actual value with a pipeworx:// citation, and describes reasoning. It also covers the error semantics (verification_error with stage/detail) and distinguishes 'could_not_verify' from 'unsupported.' This is a complete and self-contained description for the tool's complexity.

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?

The input schema covers both parameters (claim and tolerance_pct) with 100% descriptive coverage, including examples and the tolerance override semantics. The description adds no new parameter-level details beyond what the schema already states (it mentions 'percent-delta math' but that is not a parameter clarification). Baseline 3 applies because the schema does the heavy lifting.

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 purpose: natural-language claim verification against authoritative sources. It provides concrete example phrasings ('fact check', 'verify the claim that...') and explicitly names the two processing paths (SEC EDGAR fast path for company-financial claims, grounded pipeline for others). This strongly distinguishes it from siblings like ask_pipeworx or ask_pipeworx_grounded, which are general Q&A tools.

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,' giving clear context for deployment. It also notes that it replaces 4–6 sequential calls, implying it is the consolidated choice. However, it does not explicitly name alternative tools to avoid (e.g., ask_pipeworx) or state when not to use it (e.g., for open-ended 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 Phishtank 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
Disambiguation1/5

The server is named 'Phishtank' but only one tool (check_url) relates to phishing. The remaining 31 tools cover a wide range of unrelated topics (data research, prediction markets, memory, etc.), many with overlapping purposes (e.g., ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research). This makes it extremely difficult for an agent to select the right tool.

Naming Consistency2/5

Tool names mix conventions inconsistently: some use underscores (ai_visibility_check, check_url), some are camelCase (ask_pipeworx, bet_research), and others are compound phrases. There is no predictable pattern across the set.

Tool Count1/5

With 32 tools, the count is high, but only one aligns with the server name 'Phishtank' (check_url). The vast majority belong to an entirely different domain (Pipeworx tools), making the tool count severely inappropriate for the server's stated purpose.

Completeness1/5

For a phishing detection server, the tool surface is severely incomplete. It lacks essential tools like report_phish, verify_phish, get_stats, etc. The single phishing tool (check_url) is insufficient, while the other 31 tools are completely out of scope.

Resources