whale-data

Smart Money (proven cohort)

smart_money

Read-onlyIdempotent

What the PROVEN trader cohort is holding and trading, coin by coin. The cohort is not a guess at who is smart: it is Hyperliquid leaderboard accounts screened for provable profit (equity band, month and all-time PnL and ROI, volume-to-equity) and then verified against their own fills to trade at a cadence a person could follow. Two blocks, two different units, never added: positions_held is notional currently open, flow_traded is dollars executed inside the window (1h, 4h or 24h). Every row carries the wallet COUNT behind it and a thin flag when fewer than 3 cohort wallets are in it, because a one-wallet row is one person and not a cohort. cohort.rosterAgeHours is how old the MEMBERSHIP screen is (up to 24h), which is a separate fact from updated_at. Wallets whose live book could not be read are reported as unprofiled and are never counted as flat. Keyless. Descriptive market data only.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`window`	No	Which window flow_traded covers: 1h, 4h or 24h. Defaults to 24h. It does not move positions_held, which is always what the cohort holds right now, and windows_available in the reply lists what the roll-up actually published.

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	One line saying what the numbers cover, or why there are none. Read it before reporting any zero as a market reading.
`venue`	No	Which market the cohort trades on.
`cohort`	No	Who is in the cohort and how it was screened, including rosterAgeHours, the age of the membership screen.
`window`	No	Which window flow_traded covers: 1h, 4h or 24h.
`summary`	No	The answer in one plain sentence, computed from the fields below. Open the reply with this, then let the numbers back it up. Null only when there was nothing to summarise.
`coverage`	No	Which wallets could be read, and which are reported as unprofiled rather than counted as holding nothing.
`available`	No	False when this lane could not answer: a producer is dark, the pair sits outside this plan, or the argument named something we do not carry. Absent or true means the numbers are a real reading, not a guess.
`updated_at`	No	When the roll-up was published. Separate from how old the membership screen is.
`access_note`	No	What this connection could not return and what lifts it. Always pass this on to the user: it is the only place that information appears.
`flow_traded`	No	Dollars EXECUTED inside the window per coin, same row shape. A different unit from positions_held and never added to it.
`flow_withheld`	No	How many traded rows were not returned at this access level.
`positions_held`	No	Dollars currently OPEN per coin, with the wallet count behind each row and a thin flag under 3 wallets.
`windows_available`	No	The windows the roll-up actually published.
`positions_withheld`	No	How many holding rows were not returned at this access level.

TDQS

A4.7/5.0

Behavior5/5

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

The description adds substantial behavioral detail beyond the annotations: positions_held and flow_traded are never added despite different units, unprofitable/unreadable wallets are never counted as flat, and rosterAgeHours is distinct from updated_at. These edge-case disclosures are valuable and consistent with the readOnly/idempotent 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 dense and front-loaded with the core purpose, and every sentence carries useful information. It is somewhat long and includes detailed methodology that could be trimmed, but it remains well-structured and free of filler.

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 the tool has an output schema, the description does not need to explain return values, and it covers the essential behavioral nuances: cohort definition, data units, wallet counts, flags, roster freshness, and unreadable-wallet handling. Nothing critical is missing for an agent to call this tool correctly.

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?

Although the schema already covers the window parameter at 100%, the description enriches it by clarifying what window affects (flow_traded, not positions_held), the unit semantics, and that windows_available in the reply reflects what was actually published. This goes well beyond the bare enum definition.

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 verb and resource: it reports what the PROVEN trader cohort is holding and trading, coin by coin. It also distinguishes itself from other tools by defining the cohort as Hyperliquid leaderboard accounts screened for provable profit rather than a guess.

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 provides clear context for when this tool is relevant — accessing proven-cohort holdings and traded flow — and notes it is keyless and descriptive. It does not explicitly name alternative tools or state when not to use it, so it falls short of a 5.

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

All whale-data 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

A3.6/5.0

Disambiguation3/5

Many tools share the same broad purpose domains, such as market_digest vs market_overview vs market_snapshot and whale_context vs whale_profile vs whale_flow, making selection genuinely ambiguous for an agent. The long descriptions help separate them, but the sheer number of overlapping 'one-call' market and whale views still invites misselection, and whale_tape is a direct duplicate alias.

Naming Consistency4/5

Names are consistently snake_case and mostly follow a clear domain-prefix pattern: market_*, whale_*, hl_*, defi_*. Minor deviations like liquidations vs market_liquidations, liq_zones, my_access, and the deprecated whale_tape keep it from a perfect score, but the overall convention is predictable and readable.

Tool Count2/5

With 30 tools, the server exceeds the reasonable upper bound and feels heavy even for a broad data domain. Many tools could be consolidated—for instance, several one-call market summary tools and multiple whale-flow variants—without losing capability.

Completeness4/5

The tool set covers an impressively wide range of whale and market data: news, liquidations, funding, DEX activity, Hyperliquid wallets, market scans, history, and plan access. There are minor gaps such as no general price/OHLC history or per-wallet trade history beyond swaps and fills, but agents can work around these using the existing surface.

Resources

Need Help?