Hyperliquid Market Data — OHLCV, Funding Rates & Positioning (Tessera)

query_cross_section

Rank all coins for one day of a daily cross-section dataset (one row per coin per day, e.g. gold_positioning_funding_factors_1d) in a single call. Pass order_by (a numeric column), day (YYYY-MM-DD or "latest"), optional top_n (default 20), descending (default true), columns, and coins. Replaces fanning out read_dataset per coin. For a single coin's series use read_dataset.

Input Schema

TableJSON Schema

Name	Required	Description
`day`	Yes	UTC day to rank, `YYYY-MM-DD`, or `"latest"` for the newest available day.
`asset`	Yes	Dataset name. Must be a daily coin cross-section (one row per coin per `day`), e.g. `gold_positioning_funding_factors_1d`.
`coins`	No	Optional: restrict to these coins. Coins outside the caller's plan are dropped. Omit to rank every coin the plan allows.
`top_n`	No	Max coins to return (clamped to 1000). Defaults to 20.
`columns`	No	Extra columns to include per row (besides `coin`, `day`, and `order_by`). Omit to return every column.
`order_by`	Yes	Numeric column to rank coins by, e.g. a `factor_*` column. Call `describe_dataset` to see the options.
`descending`	No	Sort direction. Defaults to true — highest `order_by` first.

Output Schema

TableJSON Schema

Name	Required	Description
`day`	Yes	The day actually ranked (resolved when `day="latest"`), `YYYY-MM-DD`.
`note`	No	Advisories: latest-day resolution, coins with no row that day (coverage varies by day), coins excluded for a null/non-numeric `order_by`, and any partitions skipped on a read error.
`rows`	Yes	One object per coin, ranked; each includes `coin`, `day`, `order_by` and any requested `columns`.
`asset`	Yes
`columns`	Yes	Columns present in each returned row.
`order_by`	Yes
`coin_count`	Yes	Number of coins ranked (rows returned).
`descending`	Yes

TDQS

A4.4/5.0

Behavior3/5

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

No annotations provided, so description carries full burden. It describes a read/query operation but does not explicitly state it is read-only, or mention any side effects, authorization needs, or rate limits. However, the nature of ranking implies no destructive behavior, so it is minimally adequate.

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?

Three sentences, front-loaded with the primary action. No redundant information; every sentence contributes to clarity and differentiation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 params, output schema exists), the description covers the core use case, parameter highlights, and relationship to read_dataset. It does not explain output format but that is covered by output schema. Could mention that ranking is deterministic or pagination details, but overall sufficient.

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% with descriptions. The description adds value by explicitly stating defaults for top_n (20) and descending (true) that are not listed as defaults in the schema (schema shows null). It also summarizes the role of each parameter, complementing the schema.

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 ranks all coins for one day in a cross-section dataset, using a specific verb and resource. It distinguishes itself from sibling tool read_dataset by noting that this replaces fanning out multiple calls and directing users to read_dataset for single-coin series.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (for cross-section ranking) and when not to (for single-coin series, use read_dataset). Also implies efficiency gains over alternatives.

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

All Hyperliquid Market Data — OHLCV, Funding Rates & Positioning (Tessera) tools Inspect

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

A4.5/5.0

Disambiguation5/5

Each tool serves a distinct purpose: schema discovery (describe_dataset), bulk download (get_download_url), dataset listing (list_datasets), partition enumeration (list_partitions), cross-sectional ranking (query_cross_section), and row-level data access (read_dataset). No two tools overlap in functionality.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern (e.g., describe_dataset, list_partitions, read_dataset). The verbs are appropriately descriptive and the naming is uniform across the set.

Tool Count5/5

With 6 tools, the server is well-scoped for its purpose of providing market data access. The number is neither too few to be useful nor too many to manage, fitting comfortably within the optimal 3-15 range.

Completeness4/5

The tool set covers discovery, schema, reading, bulk download, and cross-sectional queries. A minor gap is the lack of a dedicated tool to retrieve a single coin's time series across multiple months without downloading entire partitions, but the existing tools still enable this workflow.

Resources

Need Help?