SYNTHORA sanctions-screen: sanctions screening with MATCH / CLEAR verdict over 4 official downloads (OFAC SDN primary and alias lists, UN, OpenSanctions). Multilingual, tested on Cyrillic transliterations.
| Name | Required | Description | Default |
|---|---|---|---|
| input | No | parametros del producto (JSON o texto) |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey read-only, idempotent, and non-destructive behavior. The description adds useful behavioral context beyond those hints: it names the four official downloads and states the verdict types and multilingual testing, which helps an agent anticipate coverage and limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, information-dense sentence that front-loads the core function and data sources. The 'SYNTHORA sanctions-screen:' prefix is mildly redundant with the tool name, but overall there is minimal waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Annotations and the output schema relieve the description of explaining return values or safety. However, the description never explains what should actually be passed in the generic 'input' parameter, which is a meaningful gap for a screening tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage for the single parameter is 100%, so baseline 3 applies. The description adds no additional meaning about how 'input' should be formatted or what content it should contain, but the schema already documents it as JSON or text at a basic level.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies a specific resource (sanctions screening) with a concrete outcome (MATCH/CLEAR verdict) and the underlying data sources. It is specific enough to understand the tool's function, though it does not explicitly differentiate itself from sibling tools such as vessel_sanctions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no explicit guidance on when to use this tool versus alternatives. The multilingual/Cyrillic mention offers an implied use case, but no when/when-not conditions or sibling comparisons are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The Polymarket/resolution cluster alone has eight tools (dispute_risk, market_resolution, resolution_source_feed, resolution_verdict, polymarket_resolution_watch, polymarket_odds_movers, polymarket_whales, insider_radar) with heavily overlapping responsibilities, and several risk-verdict tools also blur together. Descriptions clarify somewhat, but an agent would frequently need to read full details to avoid selecting the wrong tool.
Nearly all tools use lowercase snake_case noun-phrase names like asset_risk and sanctions_screen. A few one-word compounds (codeaudit, macrobundle, txintent) and varying prefixes break the pattern slightly, but the overall style is consistent and readable.
30 tools exceeds the 25-tool threshold and feels heavy even for a multi-domain data marketplace. Many tools are individually sold data products, and several could be consolidated — particularly the resolution/verdict/source-feed group.
The surface covers the stated domains well: maritime/chokepoint risk, Polymarket resolution and trading signals, DeFi/macro data, and transaction/identity security. Minor gaps include no registry-list/query companion to registry_watch and no historical time-series endpoint for risk verdicts, but core workflows are not dead-ended.
