Skip to main content
Glama

Data Boston

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?

The description discloses rich behavioral context beyond the annotations: it explains the fallback routing pipeline, lists the full set of possible verdicts, defines the meaning of 'could_not_verify' with its verification_error payload and explicitly warns it is not evidence, and clarifies 'unsupported' as a coverage gap. It also mentions the citation format and the fact that it replaces multiple sequential calls, providing deep insight into the tool's runtime behavior.

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 detailed yet dense, with every sentence serving a purpose. It front-loads the trigger phrases to aid pattern matching, then logically progresses from purpose to routing to verdict semantics to error handling. The use of semicolons and ellipses keeps it compact, and the final note on replacing sequential calls adds practical value without redundancy.

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's complexity (no output schema, 2 params, multiple verdicts, routing logic), the description is exceptionally complete. It explains return values (verdict, actual value, citation, reasoning), distinguishes between the two failure modes, and provides enough context for an agent to invoke the tool correctly and interpret results safely. No major gaps are apparent.

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?

While the schema already covers 100% of parameters, the description adds significant meaning, especially for tolerance_pct: it explains the default behavior (implied by claim wording, capped at 5), the override capability, and recommended values for hallucination detection (1–2) with a clear rationale. This goes beyond the schema's basic description, though the error object's exact structure is not detailed.

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 identifies the tool as a natural-language claim verification tool with specific example triggers ("Is it true that…", "fact check"), and explicitly distinguishes it from general Q&A or research tools by stating it verifies claims against authoritative sources and returns a verdict. It also details the two operational paths (SEC EDGAR fast path for company financials, grounded pipeline for everything else), making the purpose and scope highly specific.

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 provides clear usage guidance: use whenever the agent needs to check factual correctness, and it explicitly routes company-financial claims vs other claims. It also clarifies critical interpretation rules (e.g., 'could_not_verify means the check did not happen... must not be shown as one') and notes that the tool replaces 4–6 sequential calls. However, it does not explicitly name alternative sibling tools for comparison, leaving the differentiation to the reader.

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

All Data Boston 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

A4.1/5.0
Disambiguation3/5

Several tools occupy adjacent territory: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded share the same router, ask_pipeworx_beta is currently an exact duplicate, and there are multiple polymarket-related tools. The descriptions are unusually explicit and cross-reference when to use which, which keeps this from scoring lower.

Naming Consistency4/5

All tool names use lowercase snake_case and group into recognizable families (boston_*, pipeworx_*, polymarket_*), giving the set a consistent feel. However, the set mixes verb_noun names, bare verbs like remember/forget, and adjective_noun phrases like recent_changes, so it is not a strict verb_noun pattern throughout.

Tool Count2/5

At 34 tools this exceeds the 25+ threshold and feels bloated for a server with the narrow name "Data Boston"—only three tools directly concern Boston data, while the rest cover general research, prediction markets, subscription management, memory, AI visibility, and npm auditing. Most tools have a purpose, but the overall surface is not well-scoped.

Completeness4/5

For the broad data-access purpose, coverage is strong: routing, grounded verification, entity profiles, comparisons, change tracking, entity resolution, discovery, monitoring, memory, and Boston datasets are all represented. Minor gaps exist, such as no subscription update operation, no explicit fetch-by-citation tool, and limited boston_recent coverage, but agents can work around them.

Resources