Skip to main content
Glama

Recorded liquidations for one coin

coin_liquidations
Read-onlyIdempotent

Forced closes ALREADY recorded for one pair, split long versus short. These are executed liquidations, not projected levels: for where liquidations could happen next use liq_zones, and for the whole market at once use market_liquidations. The plain-English name for liquidations (identical data and credit cost). Descriptive market data only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
coinNoAlias for pair.
pairNoe.g. ETH/USD. A bare symbol like ETH also works.
hoursNoLook back this many hours, up to 720. Omit for the most recent events.
limitNoMax rows returned. Capped at 25 keyless and 1000 on a paid plan; asking for more returns the cap, and the payload says so in `capped`. count and the *_usd totals always cover the whole window regardless.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoOne line saying what the numbers cover, or why there are none. Read it before reporting any zero as a market reading.
pairNoThe pair these events belong to.
countNoHow many events fired in the whole window, not how many rows came back.
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.
sourcesNoHow the events split between the streamed exchanges and Hyperliquid, and whether the Hyperliquid part is a sample.
long_usdNoDollars of longs force-closed across the window.
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.
short_usdNoDollars of shorts force-closed across the window.
truncatedNoTrue when more rows matched than were returned, so what you have is a page and not the whole set.
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.
liquidationsNoThe events themselves, newest first: price, size in base and quote, side (long_liquidated or short_liquidated), exchange and time. A sample of the window when truncated is true.
window_hoursNoThe period the totals cover, in hours.
rows_returnedNoHow many event rows are actually in this reply.
window_minutesNoThe same period in minutes.
requested_hoursNoThe period asked for, so a page can be told apart from a period.
total_in_windowNoHow many events the window holds in total.
history_includedNoTrue when the recorded series was merged in, so a restart has not erased earlier events.
total_volume_usdNoDollars forced out across the whole window.
long_liquidationsNoCOUNT of longs force-closed. For dollars read long_usd.
rows_span_minutesNoHow far back the returned rows themselves reach.
short_liquidationsNoCOUNT of shorts force-closed. For dollars read short_usd.

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds context by noting these are executed rather than projected liquidations, that results are split long versus short, and that the data is descriptive market data only. It also mentions identical data and credit cost for the plain-English alias, which is useful beyond the 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 compact and front-loads the core distinction ('ALREADY recorded'). The alternative routing is concise, though the sentence about the plain-English name is slightly awkward and could confuse the agent given the sibling tool named 'liquidations'. Still, overall it is tight and informative.

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?

The output schema exists, so return-value details need not be in the description. Param semantics are fully covered by the schema, and annotations cover safety/idempotence. The description supplies tool-selection context, scope, and enough behavioral framing to make the tool confidently invokable.

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 schema documents all four parameters well. The description adds little directly about parameter semantics, but the 'one pair' and 'split long versus short' context helps frame the coin/pair parameters. This aligns with the baseline 3 for high schema coverage.

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 returns forced closes already recorded for one pair, split long versus short, and explicitly contrasts it with projected levels and whole-market liquidations. This gives a specific verbless but unmistakable resource scope and distinguishes it from sibling tools like liq_zones and market_liquidations.

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?

The description explicitly tells the agent when to use alternatives: liq_zones for projected liquidation levels and market_liquidations for the whole market. It also clarifies this tool is for executed, per-pair liquidations, providing both an inclusion and exclusion condition.

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

A3.8/5.0
Disambiguation2/5

The set contains at least five exact alias pairs (coin_liquidations/liquidations, market_brief/trade_context, flag_outcomes/signal_outcomes, whal_activity/whale_profile, whal_tape/whale_trades) plus many near-synonymous market_, whal_, hl_, and liquidation tools. The descriptions are excellent and cross-reference each other, but the sheer density of overlapping names makes tool selection genuinely difficult for an agent.

Naming Consistency4/5

Names are uniformly snake_case and largely follow a domain-prefix + noun convention (market_*, whale_*, hl_*, defi_*). Minor deviations exist: standalone liquidations, my_access, and duplicate aliases with different names, but the overall style is predictable and not mixed.

Tool Count2/5

38 tools is well past the 25+ threshold for a heavy toolset, and roughly ten of them are redundant alias pairs that could be collapsed into five. While the domain is broad, many one-call briefs and whale-flow variants overlap enough that the count feels inflated rather than justified.

Completeness4/5

The surface is remarkably broad for a read-only data server: price, funding, open interest, liquidations, whale flows, DeFi, options, news, signals, and access controls are all covered. Minor gaps remain, such as no explicit supported-pairs listing and some paid-tier caps that can surprise agents, but these are workaroundable.

Resources