Skip to main content
Glama

Duffel

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.

TDQS

A4.5/5.0
Behavior5/5

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

The description goes far beyond the annotations, explaining the verdict set, the meaning of could_not_verify (with verification_error), the unsupported verdict, and the automatic routing behavior. It also warns callers about misinterpreting could_not_verify. This is rich behavioral context fully complementing the annotations.

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 dense but highly structured, starting with concrete examples, then explaining the routing, return verdicts, and an important caller note. Every sentence earns its place, and the 'IMPORTANT' section is clearly flagged. No wasted words.

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?

Despite having no output schema, the description fully explains return values (verdicts, actual value, citation, reasoning) and error semantics. It also provides routing logic and explicitly states what 'unsupported' means. For a tool with this complexity, the description is complete.

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 coverage is 100% and both parameters are thoroughly described in the schema (including examples, defaults, and usage for tolerance_pct). The description itself adds no parameter-specific semantics beyond what the schema already provides, so the baseline of 3 applies.

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, with specific query examples. It distinguishes itself from sibling tools by focusing on fact-checking and explicitly noting it replaces 4-6 sequential calls, making its scope unambiguous.

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?

Explicitly states when to use: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also provides routing context (financial claims vs. other claims). However, it does not explicitly mention when not to use or name alternative tools, so it doesn't fully meet the 'when-not/alternatives' criterion.

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

All Duffel 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

A3.6/5.0
Disambiguation3/5

The set is organized into clusters (Pipeworx querying, Polymarket analysis, entity research, subscriptions, memory), but several tools within a cluster have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, deep_research, and validate_claim all answer questions, and polymarket_edges, bet_research, and polymarket_arbitrage all surface trading opportunities. The very detailed descriptions help an agent choose correctly, but the boundaries are not crisp enough for a 4.

Naming Consistency3/5

Most names are lowercase snake_case and there are consistent prefixes like polymarket_ and pipeworx_, which aids predictability. However, the verb/noun ordering is inconsistent across the set (ask_pipeworx, bet_research, entity_profile, duffel_flight_search, ai_visibility_check), and some names are noun-heavy while others are verb-first. It is readable but not a uniform convention.

Tool Count2/5

At 32 tools the surface feels heavy for a coherent server; the rubric treats 25+ as too many. Several tools are wrappers or variants of the same underlying capability (ask_pipeworx_beta, polymarket_edges vs bet_research, ai_visibility_check vs scan_competitor_ai_presence), so the count overstates real functional breadth.

Completeness3/5

The research/data side is very complete: querying, grounded verification, deep research, entity resolution, comparison, profiles, monitoring, memory, and feedback are all covered. However, the Duffel flight tool only searches and never books, so if the server is meant to be a flight agent there is a notable dead end; the broader toolkit also lacks direct CRUD for most resources beyond subscriptions.

Resources