Buildix: Hyperliquid Orderflow

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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds real substance on top: the ranking direction, annualization, the market-wide aggregate fields returned, and the $1M open-interest cutoff. It does not discuss data freshness or update frequency, which would round this out.

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?

Three sentences, front-loaded with what is returned and how it is ordered, followed by the exclusion rule and usage trigger. Every sentence contributes information; nothing is redundant with the title.

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 compensates well by enumerating the return content (ranked rates plus median, OI-weighted average, positive/negative counts) and the ranking filter threshold. An agent has everything needed to call and interpret this tool.

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?

The single 'detail' parameter has 100% schema description coverage with an enum explaining the brief/full tradeoff, so the schema carries the burden. The description adds no parameter-level detail, which is acceptable at this coverage level but earns only the baseline.

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?

States a specific verb and resource (returns Hyperliquid perpetual funding rates) plus the exact ordering (highest to most negative, annualized) and the payload (market-wide summary stats). This is clearly distinguishable from siblings like get_liquidation_levels or get_whale_positioning, which cover entirely different data.

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?

Explicitly names the triggering user intents: 'which markets pay the highest or most negative funding' and 'how funding looks across Hyperliquid.' No alternative tool or exclusion case is named, but none of the siblings is a plausible substitute, so the routing guidance is clear.

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

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

Annotations already establish readOnly/idempotent/non-destructive safety, and the description adds a genuinely important trait beyond that: the output is a model estimated from aggregate open interest with an assumed leverage mix, not an actual position record. It does not cover latency, caching, or data-age behavior for the brief mode, so it stops short of a 5.

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?

Purpose and the model caveat are front-loaded and every sentence carries information, but the 'in detail "full"' clause is wedged mid-sentence and makes the return-shape description harder to parse than it needs to be.

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 carries the return-shape burden and mostly does: clusters with price, distance and size, plus the wider range and liquidation amounts in full mode. The modeled/estimated nature is disclosed; minor gaps remain on ordering and how the leverage mix assumption is chosen.

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 coverage is 100%, so the baseline is 3, but the description adds value the schema lacks: it states that 'full' widens the range and surfaces amounts liquidated on 5/10/15% moves, which tells the agent when the mode is worth requesting.

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?

States a specific verb and resource — returns liquidation levels above and below the current price for one Hyperliquid perpetual market — and the scope (single market, current price anchored) clearly separates it from siblings like get_funding_rates or get_orderflow_snapshot.

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?

Gives explicit triggering conditions: asks where liquidations sit around the price, or how much could be liquidated on a move of a given size. It does not name when-not or alternative tools, but the sibling set covers clearly different topics, so no real ambiguity is left.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that the tool returns a 'snapshot' (implying a point-in-time view) and lists the contents, which is useful beyond the annotations. It does not discuss data freshness (the schema's 'full' detail mentions 'data age'), rate limits, or pagination, so it's adequate but not rich.

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?

Two sentences: the first is a long but front-loaded enumeration of returned data, the second gives usage scenarios. No redundant fluff, though the list of metrics is dense; still efficient and well-organized.

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?

For a read-only, zero-required-parameter screener with a fully documented schema and annotations, the description is nearly complete: it tells the agent what data is returned and when to use it. A minor gap is the absence of any mention of the two optional parameters or the 'brief' vs 'full' output difference, but the schema already covers those, so this is sufficient.

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 coverage is 100% with enum descriptions for both parameters, so the schema already fully documents them. The description does not mention 'detail' or 'sort_by' at all, adding no parameter information. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

The description specifies a clear verb and resource ('Returns a snapshot of the Hyperliquid perpetual market') and enumerates the exact metrics returned (open interest, volume, breadth, funding, top lists, gainers/losers). It distinguishes itself from siblings like get_funding_rates and get_orderflow_snapshot by covering aggregate market-wide statistics rather than a single metric.

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?

It explicitly states when to use it: 'Use it for market overviews, top movers or the most active markets.' This gives concrete scenarios and implicitly excludes narrower siblings that focus on one dimension (funding, orderflow, liquidation, whale positioning). No alternatives are named, but the intended use is unambiguous.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds value beyond them by disclosing the data provenance (computed from recent fills, order book and market context) and the fact that values are returned as categories rather than raw numbers, which shapes interpretation. It stops short of discussing staleness or rate limits.

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?

Two sentences, front-loaded with what is returned before the when-to-use clause. The middle list of metrics is dense but each item earns its place as a distinct output. Slightly long but no wasted framing.

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 carries the return-value burden and does so by naming the five returned metrics and their categorical nature. The 'detail' parameter's effect on returns is left to the schema. Adequate for a read-only snapshot tool, though it never clarifies freshness of the data.

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 the schema fully documents both 'symbol' (ticker and HIP-3 'dex:COIN' formats) and 'detail' (brief vs full). The description adds only the word 'compact', which is redundant with the schema's own explanation; 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?

States a specific verb (returns) plus resource (orderflow reading for one Hyperliquid perpetual market) and enumerates the exact outputs: CVD direction, OBI, VPIN, funding, open interest. An agent can distinguish this from siblings like get_funding_rates because the scope is explicitly a composite per-market snapshot.

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?

Explicitly says when to use it: 'when the user asks about buying or selling pressure, order book balance, flow toxicity, funding or open interest for one coin or HIP-3 market.' It does not name the sibling it overlaps with (get_funding_rates) or state exclusions, so no 5.

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

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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the safety profile is settled. The description adds real value beyond that: it clarifies the data is aggregated, that no account addresses are returned, and which accounts are tracked (Buildix's tracked large accounts).

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?

Two tight sentences: the first defines the payload and privacy boundary, the second gives the usage trigger. No filler and the key scoping ('one market', 'no addresses') is front-loaded.

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?

No output schema exists, yet the description compensates by listing the returned fields (long/short notional, account counts, bias) and the privacy constraint. Annotations cover safety and the schema covers both params, so nothing needed for correct invocation is missing.

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%, and the schema already documents both 'symbol' (ticker formats, HIP-3 dex:COIN) and 'detail' (brief vs full). The description adds no parameter-level meaning beyond 'one market', so the 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?

States a specific verb and resource: aggregated long-vs-short positioning of large Hyperliquid accounts for one market, and enumerates the returned fields (notional, account counts, bias). This is clearly distinguishable from siblings like get_funding_rates or get_liquidation_levels.

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?

Gives an explicit trigger: 'Use it when the user asks whether whales or large traders are long or short a coin.' It does not name an alternative tool or state when not to use it, but the intended context is unambiguous.

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