Skip to main content
Glama

Sgd

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

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive. The description goes far beyond this by explaining the two distinct execution paths, the exact meaning of each verdict (especially the critical distinction between 'could_not_verify' and 'unsupported'), and the presence of verification_error. It warns callers not to treat 'could_not_verify' as evidence, which is crucial behavioral context not inferable from annotations.

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 long but well-structured: it front-loads the purpose with trigger phrases, then covers routing, return format, and critical caveats. Every sentence contributes useful information, though some redundancy exists (e.g., listing six paraphrases of 'verify'). 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?

Given no output schema, the description thoroughly explains return values (verdict list, actual value, citation, reasoning), error semantics, and the 'unsupported' case. It even explains that the tool replaces multiple sequential calls, giving the agent a full mental model of its behavior. This is complete for a tool of this complexity.

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?

Schema coverage is 100%, so both parameters are already well-documented. The description adds valuable context for tolerance_pct (override behavior, default, and use case for hallucination detection) and gives concrete claim examples. This exceeds the baseline for high coverage, but does not fully compensate for missing output schema details.

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 natural-language claim verification with specific trigger phrases ('Is it true that…', 'fact check'). It distinguishes between two processing paths (SEC EDGAR fast path for company-financial claims vs. grounded pipeline for everything else), which differentiates it from siblings like ask_pipeworx_grounded or compare_entities. The verb 'verify' plus resource 'claim' is specific and 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?

The description explicitly states 'Use whenever the agent needs to check whether something a user said is factually correct' and provides clear trigger examples. It explains the structured vs. grounded routing logic, but does not explicitly name alternative tools or say when NOT to use it. Still, the guidance is strong enough to steer an agent correctly.

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

All Sgd 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
Disambiguation2/5

Several tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta (explicitly identical today), ask_pipeworx_grounded, deep_research, and validate_claim all route factual questions through similar pipelines. The polymarket_* cluster also blurs together, with arbitrage, edges, fill_risk, kalshi_spread, and bet_research all analyzing prediction-market mispricings from different angles.

Naming Consistency3/5

All names use consistent snake_case, but the verb/noun pattern is mixed: some are verb-first (compare_entities, generate_llms_txt, validate_claim), others noun-first (polymarket_edges, entity_profile, ai_visibility_check), and some are bare product names (ask_pipeworx, pipeworx_trending). Readable overall, but no single predictable convention.

Tool Count2/5

34 tools is far too many for a coherent server, especially since the server is named 'Sgd' but only 3 tools relate to yeast genetics. The remaining 31 tools span data lookup, prediction markets, memory, subscriptions, npm scanning, and llms.txt generation—an unfocused grab bag that should be split into multiple servers.

Completeness2/5

As an SGD yeast-genome server, the surface is thin: search, get_gene, and get_gene_go cover basic lookup but miss sequences, interactions, strains, homologs, and other standard SGD data. As a general data utility, the collection is broad but incoherent, with several one-off tools (generate_llms_txt, scan_dependency) that have no connection to the rest.

Resources