Skip to main content
Glama

Open Contracting

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

A4.8/5.0
Behavior5/5

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

Despite annotations already declaring readOnlyHint and idempotentHint, the description adds critical caveats: could_not_verify means the check did not happen and must not be treated as evidence, while unsupported means no source covers it. It also discloses routing behavior and the percent-delta math, going well beyond the annotation surface.

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 every sentence earns its place: examples, usage, routing, verdict list, caller warning, and efficiency note. It is front-loaded with the most important information and remains scannable despite its length.

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 no output schema, the description carries the burden of explaining return values, and it does: verdict options, actual value with citation, reasoning, and error semantics. It also covers two distinct execution paths and edge cases (could_not_verify vs unsupported), making it complete for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema already documents both parameters, but the description adds meaningful extra semantics: tolerance_pct is described as overriding the wording-implied tolerance, with a range (0.5–50), a default cap at 5, and a use-case hint (set 1–2 for hallucination detection). This enriches what the schema alone provides.

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 opens with concrete natural-language examples ("Is it true that…", "fact check", "verify the claim that…") then defines the tool as "natural-language claim verification against authoritative sources." It clearly distinguishes itself from siblings by focusing on fact-checking with a specific verdict set, rather than general search or research.

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 states "Use whenever the agent needs to check whether something a user said is factually correct" and explains the two processing paths (SEC/XBRL for company-financial claims, grounded pipeline for anything else). It does not explicitly name alternative tools or exclusion cases, but the usage context is clear.

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

All Open Contracting 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

Several tool clusters overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all serve query/discovery purposes; polymarket_edges, polymarket_arbitrage, polymarket_edge_tracker, polymarket_fill_risk, and bet_research all target prediction-market opportunity detection. ask_pipeworx_beta is explicitly identical to ask_pipeworx right now, making the distinction essentially invisible without deep description parsing.

Naming Consistency3/5

Names mix domain prefixes (oc_*, polymarket_*, pipeworx_*), action verbs (validate_claim, resolve_entity, generate_llms_txt), and plain nouns (entity_profile, recent_alerts, recent_changes). Most are readable snake_case, but there is no uniform verb_noun or domain-first convention, so the set feels stylistically fragmented rather than patterned.

Tool Count2/5

35 tools is a heavy surface for a server ostensibly named 'Open Contracting' — only 4 of the 35 tools actually relate to open contracting data. The rest sprawl across general data lookup, prediction markets, memory, subscriptions, npm scanning, and AI visibility, making the tool count feel bloated and unfocused relative to the stated purpose.

Completeness2/5

For the open-contracting domain implied by the server name, the surface is incomplete: there is coverage metadata, search, recent releases, and process history, but no direct retrieval of a single release by ID and no broader OCDS exploration tools. As a general data/Pipeworx toolkit the coverage is wide, but the severe mismatch between the server name and the actual tool set creates a significant gap between expectation and capability.

Resources