Tokenized-stock weekend gaps vs Friday close, issuer dispersion, HIP-3 perps, cross-venue funding
Scored across 1 tool
With only one tool there is no risk of misselection, so the purpose is unambiguous by construction. However, the tool bundles two distinct analyses (weekend gap vs Fri 16:00 ET reference, and cross-venue funding APR), which an agent may not expect from a single 'board' call.
The single name get_weekend_board is clear snake_case verb_noun and matches the server name. There is no multi-tool pattern to verify, which caps it short of a perfect score.
One read-only snapshot endpoint is a defensible scope for a data feed, but the surface is thin: gaps, dispersion, HIP-3 perp gaps, and funding APR all collapse into one opaque payload with no way to narrow the request.
The core domain (weekend gap plus funding APR across issuers and the matching perp) is covered, along with reference-source labeling. But there is no parameterization visible for symbol, issuer, or venue filtering, no historical snapshots, and no way to separate the two datasets, which agents will likely need.
Latest snapshot of (1) the weekend gap of tokenized US stocks vs a Fri 16:00 ET reference (Hyperliquid oracle, or token last-hour avg; each row's reference_source says which; not the official close), as a volume-weighted consensus across issuers (Ondo, xStocks, bStocks, Remora, Robinhood, Coinbase...) with cross-issuer dispersion and the matching Hyperliquid HIP-3 stock-perp gap; and (2) cross-venue funding APR for the same stock perps. All gaps in basis points vs that Fri 16:00 ET reference. Read-only, free, no key. Thin weekend liquidity; not advice.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max rows per table (default: all rows). | |
| ticker | No | Optional US ticker filter, e.g. NVDA. Case-insensitive. | |
| section | No | Which table to return (default all). | |
| include_breakdown | No | Include per-issuer / per-venue rows (default true). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly/idempotent/non-destructive, yet the description adds real context: 'free, no key', the reference is 'not the official close' and varies by row (reference_source), and thin weekend liquidity distorts readings. These are behaviorally significant caveats an agent could not get from the schema or annotations.
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?
Front-loaded with the resource ('Latest snapshot of (1)...'), which is good, but the body is a single ~90-word run-on sentence packed with nested parentheticals that is hard to parse in one pass. It would be stronger split into purpose, contents, and caveats.
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?
With no output schema, the description must carry the return semantics, and it does name the two tables, the per-row reference_source flag, and dispersion fields. Minor gaps remain around row-level fields and response shape, but an agent can call it correctly as written.
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 description coverage is 100%, so each of the four parameters is already documented (limit, ticker, section enum, include_breakdown). The description mirrors the section split (weekend gap vs funding) and explains reference_source semantics, but adds no format or default detail beyond the schema; baseline 3 applies.
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?
Names a concrete resource and its two exact contents: the weekend gap of tokenized US stocks vs a Fri 16:00 ET reference, and cross-venue funding APR for the same stock perps. The measurement basis (volume-weighted consensus across issuers, cross-issuer dispersion, matching HIP-3 stock-perp gap) is specific enough that an agent knows exactly what data it gets.
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?
Usage is only implied: it is a weekend snapshot, so context is weekend gap analysis, and 'Thin weekend liquidity; not advice' warns about interpretation. There are no explicit when-to-use/when-not statements, no alternatives (none exist as siblings), and no guidance on whether weekday calls make sense.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_weekend_boardRead-only perp funding, OI and positioning across 4 onchain venues. Not financial advice.
Stock perps & tokenized stocks: trade.xyz, Aster, Lighter, OKX, xStocks, Ondo; quotes, funding. x402
Live perp funding rates across 6 venues (Hyperliquid, Binance, Bybit, Lighter...) and arbitrage.
Perp funding rates, open interest, futures basis, IV, liquidations, order books on 8 exchanges
Add one secure layer between your agents and this server.
