Skip to main content
Glama

Whale trades feed

whale_trades
Read-onlyIdempotent

Live whale trades merged across 15 CEX venues plus on-chain DEX swaps (Ethereum, Base, Arbitrum), newest first. Keyless calls get the free shape (BTC/USD + $1M+ CEX trades live, other pairs delayed 30 min, DEX swaps $250K+) and up to 25 rows; a paid developer plan lifts the shape to every pair with no delay and up to 500 rows here (deeper pages on the REST API). Descriptive market data only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
coinNoFilter to one coin, for example BTC. A pair like ETH/USD works too, the quote leg is dropped. One symbol, not a list. Omit for every coin.
pairNoAlias for coin.
limitNoMax rows returned. Capped at 25 keyless and 500 on a developer plan; asking for more returns the cap, and the payload says so in `capped`.
sourceNoWhich markets to read: cex for the 15 streamed exchanges, dex for on-chain swaps on Ethereum, Base and Arbitrum, all for both merged. Defaults to all.
min_usdNoSmallest trade to return, in US dollars, for example 5000000 for $5M and up. Omit for everything already large enough to count as whale-sized. Keyless calls hold on-chain swaps to $250K and up regardless. A size filter runs after the fetch, so scan_capped in the payload states whether the search reached its own ceiling and older matches may exist.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
coinNoThe coin filter that was applied, or null for every coin.
noteNoOne line saying what the numbers cover, or why there are none. Read it before reporting any zero as a market reading.
countNoHow many rows this reply carries.
cappedNoPresent only when an argument was cut down to a ceiling. Absent means nothing was clamped, so a smaller number than you asked for is the data and not a limit.
sourceNoWhich markets were read: cex, dex or all.
tradesNoThe matching trades, newest first. A CEX row carries pair, exchange, price, size and side; an on-chain row carries the token, the wallet and the dollar size. Every row carries source.
coveredNoFalse when the coin asked for is not one this feed streams, so nothing was searched. That is different from a quiet market.
matchedNoHow many trades matched the filters before the row cap was applied.
availableNoFalse 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.
scan_noteNoSays the search stopped at its ceiling, so this is not the complete set for the window.
truncatedNoTrue when more rows matched than were returned, so what you have is a page and not the whole set.
depth_noteNoHow far back the data behind this answer reaches.
access_noteNoWhat this connection could not return and what lifts it. Always pass this on to the user: it is the only place that information appears.
scan_cappedNoTrue when the search hit its own depth ceiling, so older matches may exist that were never looked at.
scanned_rowsNoHow deep the search went before filtering. Present only when a coin or size filter ran.

TDQS

A4/5.0
Behavior5/5

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

Annotations already declare readOnly and idempotent behavior, and the description adds meaningful behavioral context: free-tier rows/delays, cap behavior, source merging, novelty ordering, and the note that it is 'descriptive market data only.' No contradictions with annotations exist.

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?

Three sentences with useful information front-loaded: scope and ordering come first, then plan/limit details, then the descriptive-only caveat. The middle sentence is dense but every clause carries relevant operational meaning.

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?

With an output schema present and all five parameters fully documented in the schema, the description covers the remaining context: venue sources, free vs. paid data shape, delay conditions, row limits, and the descriptive nature of the data. An agent can invoke this tool correctly from the combined schema plus description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are already fully documented. The description reinforces limits and plan-dependent behavior, but does not add substantial meaning beyond the schema's own parameter descriptions.

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 states a specific resource ('whale trades'), a precise scope ('merged across 15 CEX venues plus on-chain DEX swaps'), and the ordering behavior ('newest first'). It also gives the free vs. paid shape, which makes it clearly distinguishable from sibling feed-like tools such as whale_tape or onchain_whales.

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

Usage Guidelines2/5

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

No guidance is given on when to choose this tool over alternatives such as whale_tape, whale_radar, or onchain_whales. The plan-level distinction (keyless vs. developer) is operational, not a decision rule among sibling tools.

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

Try in Browser

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