whale-data

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

Annotations already indicate a safe, read-only, idempotent operation. The description adds valuable behavioral context beyond annotations: it specifies the sentiment score range (-100 to +100), that only one coin is covered per call, and the parameter description clarifies the difference between absence of data (covered:false, null sentiment) and a neutral reading. This aligns with annotations and enriches understanding.

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 concise sentences, front-loaded with the core purpose, and every phrase earns its place. No redundancy or filler.

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?

Given the simple tool with two parameters, a comprehensive output schema, and robust annotations, the description covers the necessary context: scope (one coin), sentiment range, macro picture, and read-only nature. The parameter descriptions handle edge cases like unsupported coins and pair normalization, making this complete.

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 schema description coverage is 100%, with both 'coin' and 'pair' already explained in detail (defaults, alias, pair handling, absence behavior). The main description adds little beyond the schema, so it appropriately relies on the schema for parameter meaning. Baseline 3 is correct.

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 clearly states the tool's function: fetching recent crypto headlines with a pre-computed sentiment score for a specific coin, plus a macro picture. This distinguishes it from sibling tools like market_snapshot or whale_trades by highlighting the news and sentiment focus.

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?

The phrase 'Descriptive market data only' implies this is a read-only informational tool, but there is no explicit guidance on when to choose it over alternatives or when not to use it. The description implies usage for news/sentiment context but does not provide exclusions or alternative recommendations compared to sibling tools.

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, destructiveHint=false. The description adds valuable behavioral context: keyless access, descriptive market data only, and clarifies that 'count' and 'total_usd' cover exactly the returned rows with a 'window' field, avoiding misinterpretation of fixed 24h figures. This exceeds the annotation baseline.

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, each dense with information: scope, event distinction, and metric semantics. No fluff, front-loaded with the most important purpose, and every sentence earns its place.

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?

Given an output schema exists and annotations cover safety, the description covers scope, event type, chain availability, metric semantics, and alternative tool differentiation. It is complete for a read-only filtered tool with simple parameters.

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% for both parameters, providing full documentation. The description further clarifies the 'limit' parameter's behavior (defaults, hard ceiling) and the 'chain' parameter's refusal behavior, adding value beyond schema. Baseline 3 is elevated to 4 due to meaningful extra context.

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 states a specific verb ('repaid debt and seized collateral') and clearly names resources (Aave V3, Morpho Blue on Ethereum, Arbitrum, Base). It distinguishes from the sibling 'liquidations' tool by explicitly saying it's a different event and never summed with one.

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 provides clear context on what the tool covers (lending liquidations vs perp liquidations) and names the alternative 'liquidations' tool for perp liquidations. It does not explicitly say 'when not to use' beyond the differentiation, but the guidance is specific enough to select correctly.

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 mark this as read-only/idempotent/non-destructive. The description adds meaningful context beyond that: it discloses that keyless access returns totals with swap USD withheld, while a developer plan returns the full table. This is useful behavioral detail not present in structured fields.

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 the tool's purpose, followed by useful tier details. No filler or redundancy; every sentence contributes.

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 parameters, strong annotations, and an output schema present, the description fully covers what the tool does and its behavioral quirks. The access-tier distinction is a nice extra that makes it self-contained.

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 tool has zero parameters, so the schema covers everything trivially. The description adds context about access-tier differences but doesn't need to explain parameter semantics. Baseline for 0 parameters is 4, which fits.

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 opens with 'One-call on-chain DEX state across Ethereum, Base and Arbitrum', clearly stating the resource and scope. It enumerates specific metrics (24h volume, TVL, top tokens, whale swap activity), distinguishing it from sibling tools like market_overview or whale_trades.

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?

The 'One-call' phrasing implies a high-level overview use case, and 'Descriptive market data only' signals a non-trading context. However, it does not explicitly mention when not to use this tool or point to alternatives, which would push it to a 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds valuable context beyond annotations: the 7% coverage limit, the meaning of tracked:false, and the 'descriptive market data only' caveat. No contradiction with annotations.

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, each purposeful: the first states the tool's function, the second disambiguates from a sibling, and the third discloses the critical coverage limitation. No wasted words; information is front-loaded and directly relevant.

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?

Given the output schema exists (so return values are documented) and annotations cover safety, the description provides the essential remaining context: the tool's scope (Ethereum/Base/Arbitrum), the sibling distinction, and a realistic coverage limitation that affects interpretation. This is complete for an agent to use the tool correctly.

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 already fully describes both parameters, including address format and limit defaults/cap. The tool description reinforces the address/vs Hyperliquid distinction but does not add new parameter-specific meaning beyond what is in the schema, so baseline 3 is appropriate.

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 opens with 'One Ethereum, Base or Arbitrum address: its recorded DEX swaps, net flow per token and activity pattern,' clearly identifying the resource (wallet address) and specific actions (DEX swaps, net flow, activity pattern). It also explicitly distinguishes from hl_wallet, ensuring no confusion among siblings.

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 gives explicit direction to use hl_wallet for Hyperliquid accounts ('For a Hyperliquid ACCOUNT use hl_wallet instead') and warns about the 7% coverage limit with the instruction to 'state it once when the answer turns on it,' which guides when and how to interpret results. This is strong usage guidance.

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 read-only and non-destructive behavior. The description adds valuable context about data freshness ('logged live and never backfilled') and scope ('descriptive market data only'), which goes beyond the structured annotations. No contradiction.

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?

The description is two sentences, front-loaded with the main purpose, and every clause adds value without waste. It is concise yet informative.

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?

Given the output schema exists and the input schema covers all parameters, the description provides sufficient context about the tool's data scope and freshness. It could mention the time window or type filters, but those are already fully documented in the schema, so no significant gap remains.

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 all parameters are thoroughly described in the input schema. The tool description does not add additional parameter context, so the baseline of 3 is appropriate.

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 clearly states the tool returns recently fired signal-ledger flags with fire-time and later price outcomes. It uses a specific phrase ('signal-ledger flags') that distinguishes it from sibling tools like whale_trades or market_screener, and clarifies it is descriptive market data only.

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?

The phrase 'logged live and never backfilled' provides clear context that this tool is for recent data only, and 'Descriptive market data only' signals it is not for trading actions. While no alternatives are explicitly named, the limitations are clear enough to guide appropriate use.

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 read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond this: keyless access, that rates depend on venue-provided data, and that it is descriptive only. This enriches the behavioral understanding without contradicting 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: three short sentences that each add distinct information—what the tool provides, access requirements, and data nature. There is no redundancy, and the most important information 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?

Given the simple nature of the tool, the description covers the core purpose, limitations, and access. An output schema exists (per context signals), so return values are already defined. It could be more explicit about when to use it relative to other market data tools, but it is largely complete for this context.

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 input schema has 100% coverage, with the 'pair' parameter description explaining defaults, bare symbol handling, and the non-comparability of rates due to venue-specific intervals. The main description adds little new parameter semantics, so the baseline of 3 is appropriate.

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 clearly identifies the tool as providing per-venue funding rates for a single trading pair, including predicted next rate and payout time where available. This resource is unique among the sibling tools, none of which mention funding rates, so it distinguishes the tool effectively.

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?

The description gives clear context: the tool is keyless on any streamed pair and is descriptive market data only, implying it is safe to use for read-only information needs. However, it does not explicitly mention when not to use it or name alternative tools, though the unique purpose makes such guidance less critical.

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 this as a safe, read-only, idempotent operation. The description adds valuable behavioral context beyond annotations: it discloses that keyless access returns only top rows and reports how many are withheld, while a developer plan returns the full board. This explains tier-based limitations and result shaping, which is not visible in schema or annotations.

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?

The description is two sentences, front-loaded with the core content (equity, open notional, etc.) and then adds access-tier behavior. Every phrase earns its place; there is no fluff or repetition of schema information.

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?

Given the tool has no parameters and an output schema exists (which defines the return structure), the description adequately covers what the board contains and how access limits work. It is complete for a simple read-only aggregate tool, and the 'Descriptive market data only' note sets expected limitations.

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 tool has zero parameters, so schema coverage is complete by default. The baseline for 0-param tools is 4, and the description adds no parameter-specific information because none is needed. It appropriately focuses on output content and access tiers.

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 clearly defines the tool's output: tracked Hyperliquid whale accounts with equity, open notional, leverage, net bias, and per-coin crowding. It distinguishes itself from sibling tools (e.g., hl_whales) by focusing on a 'board' of tracked accounts and explicitly stating the keyless vs. developer plan return behavior.

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?

The description implies usage as a read-only informational board ('Descriptive market data only') and explains access-tier behavior, but it does not explicitly state when to choose this over other whale-related sibling tools like whale_radar or whale_flow. It lacks explicit exclusions or alternative recommendations.

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?

Beyond the annotations (read-only, idempotent, non-destructive), the description discloses access-tier behavior: live book is public and keyless, while computed history and the full fill trail require a developer plan. It also clarifies that 'Descriptive market data only' indicates non-actionable data. Additionally, the parameter description (in the schema, integrated here) explains keyless calls receive only 3 fills regardless of request, which is a concrete behavioral trait. There is no contradiction with annotations.

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?

The description is two sentences, front-loaded with the core function and data fields, followed by access-tier and data-type context. Every clause contributes meaningful information ('Descriptive market data only' adds a clarity caveat). It is efficient without being terse.

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?

The tool has an output schema, so return formats are documented separately. The description covers the main payload components (positions, equity, PnL, fills), the access-tier distinction (keyless vs. developer plan), and the data's descriptive nature. It also leverages the parameter descriptions to clarify edge cases. This is complete for the tool's complexity.

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 input schema description coverage is 100%, and both parameters have detailed descriptions in the schema itself (e.g., address format, limit defaults/ceiling, keyless behavior, tracked:false semantics). The tool's description text does not add significant parameter-level information beyond what the schema already provides, so a baseline of 3 is appropriate when schema carries the load.

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 opens with 'One Hyperliquid account' and enumerates the exact data provided: live positions, equity, leverage, net bias, unrealized PnL, and recent whale-sized fills. This clearly identifies the resource and scope, distinguishing it from sibling tools like hl_whales that likely cover multiple accounts. The purpose is specific and immediately understandable.

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?

The description gives clear context on access tiers ('The live book is public on Hyperliquid so it stays keyless; computed history ... and the full fill trail need a developer plan'), which helps users know what to expect. However, it does not explicitly name alternative tools or state when not to use this tool. The 'One Hyperliquid account' phrasing implies use for single-account queries, but an explicit alternative (e.g., hl_whales for many wallets) is missing.

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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds key context: it is 'Keyless. Descriptive market data only,' and it explains the unique trait that both sides of a fill are named, enabling followability. This goes beyond the annotations without contradicting them.

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?

The description is concise and front-loaded: the first sentence states the core purpose, the second explains the unique value and points to hl_wallet, and the final fragments state keyless/descriptive. Every clause earns its place with no redundancy.

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 an optional-filter read-only list tool, the description is complete: it specifies the data returned, the unique data source, the access requirement (keyless), and provides a pointer to a related tool. Since an output schema exists, return-value details don't need to be in the description.

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 detailed parameter descriptions, including coin's handling of k-prefixed markets and limit's default/ceiling. The description itself adds no extra parameter-specific semantics beyond the schema, so the baseline of 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?

The description clearly states that the tool returns 'recent whale-sized Hyperliquid fills' with the unique feature that 'wallet address attached' to each fill. It distinguishes this from siblings by noting Hyperliquid's public feed names both sides, making fills followable, and explicitly references hl_wallet. The purpose is specific and well differentiated.

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?

The description gives clear context: it is keyless and provides descriptive market data, and it points to hl_wallet for following a live book. It explains that this is the venue for wallet-attached fills, which indicates when to use it. However, it doesn't explicitly state when not to use it versus other whale-related siblings.

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 mark the operation as read-only, idempotent, and non-destructive. The description adds substantial behavioral context: live tape merged with recorded series so history is never erased, long liquidations are sell-side events, and truncation semantics with window_minutes and total_in_window are clearly explained.

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?

The description is dense but not bloated; every sentence contributes distinct information about behavior, parameters, or edge cases. It front-loads the core purpose and then systematically details parameter semantics and truncation handling, making it appropriately sized for the tool's complexity.

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?

Given the output schema exists, the description need not enumerate return values. It covers period selection, truncation behavior, parameter caps, the long/short event meaning, and the 'Descriptive market data only' scope, providing a complete picture for an agent.

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 schema already describes all four parameters with 100% coverage, giving a baseline of 3. The description adds meaningful semantics beyond the schema by explaining that hours=24 means 'today', that window_minutes covers only returned rows when truncated, and that limit capping is reported in 'capped' while totals cover the whole window regardless.

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 clearly identifies the tool as returning liquidation trades for a pair, with long/short breakdown and historical persistence. It distinguishes itself from sibling tools by focusing on pair-specific liquidation tape and explaining the merge of live and recorded 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?

It explicitly explains when to pass hours (for a lookback period like 'today') and what happens without it (recent rows with window_minutes). It does not name alternatives or exclusion criteria, but the parameter usage context is clear enough for an agent to decide how to invoke it.

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, idempotentHint, and destructiveHint false. The description adds valuable behavioral context beyond annotations: it is modeled from leverage assumptions, is clearly labeled as a projection, and provides 'descriptive market data only.' It also exposes plan-dependent limitations, which is useful for setting expectations.

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?

The description is two sentences, front-loaded with the core purpose, and efficiently packs essential details about projection nature and plan tiers. Every sentence earns its place with no filler or repetition.

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?

Given the output schema and rich annotations, the description is complete enough for selection. It covers what the tool does, its limitations, and the meaning of free vs. developer plan access, which is adequate among 27 sibling tools.

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%, with each parameter (coin and pair) already well-documented, including plan behavior in the pair description. The description itself adds no additional parameter-level semantics, so the baseline of 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?

The description clearly identifies the tool as a projected liquidation level book for one pair, explicitly distinguishing it from executed trades and actual liquidation feeds. It provides a specific resource and scope, and the phrase 'projected' plus 'not executed trades' separates it from siblings like liquidations or market_liquidations.

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?

Clear context is provided: use this tool for projected liquidation levels for one pair, with plan-based limitations (keyless free pairs without cascade chains, active developer plan full snapshot). However, it does not explicitly name alternative tools or state when not to use it, so it lacks the explicit exclusions needed for a 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 indicate read-only, idempotent, and non-destructive behavior. The description adds that data may be stale, pointing to as_of_day and stale fields, and notes that next-day outcome stats exist only where enough events are available. This is useful context beyond annotations, though it does not fully explain how to interpret staleness.

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?

The description is two sentences, front-loaded with the core purpose, followed by a clear caveat about data staleness. Every sentence earns its place with no redundancy.

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 input parameters and an output schema available, the description need not explain return values. It covers the key elements: what the tool reveals, the staleness caveat, and the descriptive-only nature. It could clarify what 'pairs' refers to, but that is domain-specific context rather than a critical gap.

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 tool has zero parameters, so the baseline is 4. The description mentions as_of_day and stale but these are response fields, not inputs. No additional parameter semantics are needed.

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 clearly states it identifies pairs at record highs/lows or in the top/bottom 5% for funding, open interest, or liquidations relative to their own history, and provides next-day outcome stats. This is a specific, resource-focused purpose that distinguishes it from siblings like market_overview or market_history.

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 provides context that the tool covers the latest recorded day, not necessarily today, and instructs to check as_of_day and stale before treating data as current. However, 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.

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

Annotations already indicate read-only, idempotent, and non-destructive. The description adds valuable behavioral context: data is archived since specific dates, keyless calls are capped at 30 days and the payload reports caps via 'capped', and both lanes settle several days behind live data. This goes well beyond what annotations provide and is not contradicted by them.

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?

The description is concise and front-loaded, using three sentences to communicate the two modes, archive dates, access limits, and data nature. Every sentence adds essential information without redundancy or fluff.

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?

Given the tool's two-mode complexity, the description covers access tiers, data lag, and the distinct handling of coin vs pair. Since an output schema exists, the lack of return-value detail is acceptable. Annotations cover safety, and the description fills the behavioral context, making it complete for an agent to select and invoke.

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%, and each parameter has a detailed description explaining its meaning and defaults. The tool description further clarifies the relationship between 'coin' and 'pair' as distinct questions and how they interact (coin overrides pair), adding extra semantic depth beyond the schema. This justifies a score above the baseline of 3.

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 states the tool provides daily historical data for either market metrics (funding, open interest, price, liquidations) for a pair, or whale buy/sell flow for a coin, with archive start dates. It clearly distinguishes the two usage modes and is specific about the resource and data type.

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?

The description provides clear context on access limits (keyless 30 days, paid plan full archive) and notes the data is descriptive only, implying it is for historical reference rather than live trading. However, it does not explicitly name alternative tools or give when-not-to-use guidance, so it stops short of a full 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?

Beyond the annotations (read-only, idempotent, non-destructive), the description discloses critical caveats: data only from venues publishing liquidation feeds, the Hyperliquid share is a sample, totals are a floor, and long dollars represent sell-side pressure. This is exactly the kind of behavioral context annotations do not provide.

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?

The description is dense but every sentence adds unique value: scope, data caveats, separate lanes, and interpretation. It is structured logically, starting with the definition, then limitations, then usage warnings, and ending with a clarifying statement about descriptive data. No filler.

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?

Given the tool has an output schema and zero parameters, the description carries the responsibility of explaining the nuanced data behavior. It covers data provenance, aggregation method, the floor nature of totals, the unique named_liquidations, and the separation of lending liquidations. This is complete for a tool of this complexity.

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 input schema has zero parameters, so the baseline is 4 per the rubric. The description does not need to add parameter detail because there are none, and the schema coverage is effectively 100%.

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 opens with a specific verb and resource: "The whole market's forced closes in one call rather than per pair." This clearly distinguishes it from per-pair liquidation tools, and the detailed breakdown (24h dollars/counts, long vs short, hourly, ranked by coin) makes the tool's purpose unambiguous.

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?

The description states the tool is market-wide rather than per-pair, implying it should be used when a whole-market view is needed. It also provides an explicit when-not: lending_liquidations must never be added to perp numbers. However, it does not name specific sibling tools as alternatives, so it stops short of the highest bar.

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/destructive-safe, and the description adds relevant behavioral notes: 'Descriptive market data only' reinforces non-transactional use, and 'no paging needed' clarifies single-row behavior. It doesn't go into pagination limits or return size, but annotations lower the bar.

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, first lists contents, second explains coin parameter behavior. Every clause carries information; no fluff or repetition of schema field names.

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?

Given the output schema and rich annotations, the description needn't describe return values. It covers the main feature set (totals, whale flow, regime, ranking) and the coin lookup path, making it sufficient for an overview 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?

Schema coverage is 100%, so the baseline is 3, but the description enriches the coin parameter by explaining the direct row retrieval and the 'no paging needed' property. The mention of 'top rows by volume' also clarifies the ordering semantics not fully explicit in the schema.

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 opens with 'One-call market scan' and enumerates concrete outputs (totals, whale net flow, BTC risk regime, top rows by volume), giving a specific verb-resource pairing. It also notes coin-level lookup, which distinguishes it from generic screener siblings.

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 clearly implies use for a quick, comprehensive market overview via 'One-call market scan' and notes the coin shortcut for single-symbol queries. It does not name any sibling as an alternative, so there's no explicit when-not-to-use guidance, but the context 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is established. The description adds the key behavioral nuance that band comparisons are 'vs each pair's OWN recorded days' and that the whale-flow multiple is relative to the coin's own average, which is useful context beyond the annotations. However, it doesn't describe pagination, rate limits, or exact output behavior beyond what schema/output schema already provide.

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?

The description is a dense two-sentence structure that front-loads the core action ('Screen every recorded pair') and then lists filters. It earns its length by conveying the discovery call scope and relative-band logic, though the parenthetical enumeration of band values (record high, top 5%, etc.) duplicates schema content and could be shortened without losing value.

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?

The tool has 6 parameters, no required ones, full schema coverage, an output schema, and clear read-only annotations. The description supplies the missing high-level context: this is the cross-market discovery screen ('every recorded pair in one call') and filters are self-relative. It is complete enough for an agent to decide when to invoke and what to expect, without needing to explain return values due to the output schema.

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?

All 6 parameters have complete, detailed descriptions in the schema (100% coverage), so the description does not need to compensate. The description reiterates filter concepts like 'funding_band / oi_band' and 'whale_mult_min' but adds no new parameter-level meaning beyond summarizing what the schema already documents. Baseline 3 is appropriate.

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 opens with 'Screen every recorded pair in one call', giving a specific verb, resource, and scope. It then enumerates the filtering dimensions (funding/oi bands, whale-flow multiple, radar-unusual) and ends with 'The discovery call. Descriptive market data only.', which distinguishes it from other market tools like market_snapshot or whale_trades.

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?

The phrase 'The discovery call' clearly signals when to use this tool: when exploring across all recorded pairs. It also notes 'Descriptive market data only', excluding trade execution or data modification. However, it stops short of explicitly naming alternatives for different use cases (e.g., 'for pair-specific data use market_snapshot'), so it lacks formal exclusion guidance.

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 and idempotentHint, so the safety profile is known. The description adds valuable context beyond annotations: access-tier differences (keyless vs paid plan), data source variability ('from the venues that publish them'), and coverage behavior for non-streamed pairs. No contradiction.

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?

The description is extremely concise: two sentences. The first sentence front-loads the core purpose and data points; the second covers access tiers and data nature. Every word earns its place with no redundancy.

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 an output schema present, the description adequately covers the tool's scope, data categories, access tiers, and coverage caveats. Minor details like data freshness or specific venue names are optional and not critical given the schema.

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 thorough descriptions for both parameters including defaults, aliases, and access-tier behavior. The main description adds no additional parameter-specific meaning, so baseline 3 is appropriate.

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 clearly states the tool's function: 'One-call market state for a pair' and lists specific data points (last price, 24h stats, average funding rate, open interest, liquidation totals). This distinguishes it from sibling tools like market_history or market_liquidations by emphasizing a combined 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?

The phrase 'One-call' implies use for a quick comprehensive view, and 'Descriptive market data only' clarifies it is read-only. However, there is no explicit mention of alternatives or when not to use this tool, leaving the agent to infer comparative usage from sibling names.

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?

Beyond the readOnlyHint and idempotentHint annotations, the description adds critical behavioral context: it is free to call and never metered, and only an active developer plan lifts caps. It also explains common misconceptions, giving the agent full transparency into side effects and limitations.

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?

The description is a dense run-on sentence, covering many details but lacking clear structure or breaks. It is informative but could be more concise and front-loaded; the title helps, but the body is a wall of text.

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?

The description fully covers the tool's purpose, usage triggers, and output semantics (credits, caps, locked items, upgrades). With an output schema present and no parameters, this is complete for an AI agent to select and invoke the tool correctly.

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 tool has zero parameters, and schema coverage is 100%. The description adds no parameter-specific info because none is needed; a score of 4 aligns with the baseline for parameterless tools.

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 clearly states what the tool does: it shows what the connection can and cannot see, including plan status, credits, tier, caps, locked features, and how to lift limits. It uses specific verbs and resources, distinguishing it from all sibling tools.

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 tells when to call it: when the user asks about what they get, credits, capped results, or how to upgrade. It also clarifies exclusions (CoinLobster Pro website subscription does nothing, free API key does nothing), providing strong guidance on when not to use it.

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 and idempotentHint. The description adds useful context: 'Keyless' indicates no authentication needed, and 'Descriptive market data only' clarifies that the output is raw data rather than signals or advice. No contradiction with annotations.

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 cover purpose, data payload, filters, authentication, and data nature. Every word contributes, no fluff, and key information 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?

An output schema exists, so return values are documented elsewhere. The description adds the data fields carried by each swap and the keyless/descriptive nature. It is adequate for a read-only data tool, though it does not explicitly differentiate from the many sibling whale tools.

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 each parameter is already documented in detail. The description summarizes filtering options ('chain, coin or minimum size') but adds no syntax or semantics beyond what the schema provides. Baseline 3 is appropriate.

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 uses a specific verb 'Executed' and identifies the resource as 'DEX whale swaps' on Ethereum, Base, and Arbitrum. It also lists the exact data fields (wallet, DEX, token, USD size), making it clearly distinguishable from other whale-related tools.

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?

The description gives clear context: it is keyless (no auth required), provides descriptive market data only, and can be filtered by chain, coin, or minimum size. However, it does not explicitly name alternatives or state when not to use this tool relative to siblings like whale_trades or whale_flow.

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 read-only/idempotent behavior, but the description adds extensive behavioral context beyond annotations: cohort screening criteria, the distinct meanings of positions_held and flow_traded, wallet-count flags, rosterAgeHours semantics, treatment of unprofiled wallets, and the keyless/descriptive nature. No contradictions with annotations.

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?

Although the description is long, every sentence earns its place by explaining the cohort definition, the two data blocks, field interpretations, edge-case handling, and time semantics. It is well-structured and front-loaded with the core value proposition.

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?

Given the complexity of the domain and the presence of an output schema, the description fully equips an agent to understand what the data represents, how to interpret edge cases, and how to use the optional parameter. It leaves no obvious gaps in operational understanding.

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 parameter window is already described in the schema, but the description adds crucial semantics: it only affects flow_traded, not positions_held, and windows_available in the reply indicates actual roll-up coverage. This goes beyond the schema's own description and prevents misinterpretation.

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 clearly identifies the tool's purpose: exposing what the PROVEN trader cohort holds and trades, coin by coin. It uses a specific verb+resource construction and distinguishes itself from sibling tools like whale_* by explaining the cohort's screening methodology.

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?

The description gives clear context for when to use the tool—when an agent needs insight into the positions and flows of a provably profitable trader cohort. It does not explicitly mention alternatives or when not to use, but the detailed methodology and semantics make the tool's niche 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 readOnlyHint, idempotentHint, and non-destructive behavior. The description adds that the tool 'fuses' multiple data sources and reports the overexposed side, and it reiterates the descriptive nature. It also flags the paid plan requirement, which is a behavioral prerequisite. No contradiction with annotations.

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?

The description is short and front-loaded with the primary purpose, followed by caveats. However, 'Descriptive' appears twice ('Descriptive, not a trade signal' and 'Descriptive market data only'), creating slight redundancy. Otherwise it is efficient.

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?

Given the tool's moderate complexity and the presence of an output schema, the description covers the key inputs (per pair), the composite nature of the score, and the access prerequisite. It does not need to detail return values since an output schema exists. This is complete for its purpose.

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 detailed descriptions for both coin and pair, including default behavior and developer plan requirement. The main description only mentions 'per pair' and the plan requirement, adding little beyond the schema. A baseline score of 3 is appropriate.

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 clearly states the tool provides a fused 0-100 crowding score per pair, listing contributing factors (funding, long/short accounts, taker imbalance, OI trend) and the overexposed side. It also clarifies that it is descriptive, which distinguishes it from signal-oriented tools. This is specific and unambiguous.

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?

The description explicitly says 'not a trade signal' and 'Descriptive market data only', indicating when not to use it for trading decisions. It also notes the paid developer plan prerequisite. However, it does not name alternative tools for comparison, so usage context is clear but lacks explicit exclusions beyond the trading disclaimer.

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 and idempotentHint=true, but the description adds valuable behavioral context: compact mode returns a one-liner instead of JSON, paid plan gates advanced analytics, and it explicitly states 'Strictly descriptive: state plus recorded history, no advice.' This goes beyond annotations, though some behaviors like locked_layers are only in the schema.

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?

The description is dense but well-structured: starts with the core purpose, then lists components, then options (compact), then paid plan, then disclaimers. Each sentence adds information, though it is somewhat long and could be tightened without losing content.

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 an output schema present and annotations covering safety, the description covers the main data components, the compact alternative, paid vs free limitations, and the descriptive nature. It is quite complete for a complex composite tool, though it could better explain free vs paid data shape (e.g., locked_layers) directly in the description.

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. The description mentions position_usd in the context of carry arithmetic and compact, but these are also covered in the schema details. It does not add significant new meaning beyond what the schema already provides.

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 clearly states the tool returns a pre-trade context blob with specific components (price, funding, open interest, whale flow, liquidations) on any streamed pair keyless. This distinguishes it from specialized siblings like funding_matrix or whale_flow, and the title 'One-call trade context' reinforces its purpose.

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?

The phrase 'pre-trade context blob in one call' indicates when to use it (broad pre-trade overview), and the schema adds keyless vs paid usage context. However, it does not explicitly mention alternative tools or when not to use this tool, so it lacks explicit exclusions.

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 reassure read-only/idempotent safety; the description adds valuable context: keyless access returns only multiples/records, USD magnitudes require an active plan, and it labels the data as 'descriptive only'. This goes beyond the structured annotations.

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 dense sentences convey the core purpose, input/output format variations, access constraints, and data nature. No wasted words; front-loaded with the key concept.

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?

Given the tool's moderate complexity, a rich output schema, and annotations, the description covers use case, input variations, return shapes, access limitations, and data type in a compact form. It is fully adequate for an agent to select and call the tool correctly.

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 descriptions already cover both parameters (coin and pair, with list behavior). The description adds practical semantics: comma-separated list returns {coins:[...]}, single coin returns flat object, and omitting coin gives top 15. This enriches the schema beyond its literal description.

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 gives a specific verb+resource: 'Per-coin whale flow vs that coin's OWN logged history' and explicitly calls it 'the is this unusual for THIS coin call', distinguishing it from sibling tools like whale_flow. This clearly communicates the tool's unique function.

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 clearly indicates when to use it (the per-coin 'unusualness' call) and describes list usage for portfolio briefs. However, it does not explicitly name sibling alternatives or state when NOT to use it, but the context is strong.

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 read-only/idempotent/non-destructive, so the description's added value lies in clarifying the data is descriptive (not predictive) and that the window rolls. This is useful beyond the annotations, but it does not disclose response size or pagination behavior.

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 the core function, no filler. Every word earns its place, making it concise and well-structured.

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?

Given the rich annotations, detailed schema, and existence of an output schema, the description covers the key aspects: what data, for one coin, split, time window, and nature (descriptive). It could mention the rolling window's cap, but that is already in the schema, so it is complete for this simple 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?

Schema coverage is 100%, with detailed descriptions for coin, pair, and hours, including defaults and caps. The description adds no new parameter semantics beyond confirming a single coin is expected, so 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?

The description clearly states the tool provides hourly buy/sell USD flow buckets for a single coin, split by CEX and DEX, over a rolling window. This is specific and distinguishes it from sibling tools like whale_trades (individual trades) or market_snapshot (general overview).

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?

The description does not explicitly name alternatives, but 'Descriptive market data only' signals it is for factual historical flows, not predictive signals, helping the agent choose among market analysis tools. The rolling-window scoping gives context for time-based queries, though it lacks explicit 'when not to use' guidance.

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 and idempotent hints, but the description goes well beyond by clarifying edge-case semantics: pressure.state null with named reasons must be reported as 'not enough to say', venues.partial dollars are unknown and not zero, hoursCovered appears only for partial windows, and price-coverage figures are omitted when already satisfied. This rich context prevents misinterpretation and adds genuine value 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is lengthy, but each sentence carries meaningful operational content and it front-loads a broad summary before diving into nuanced caveats. It is not a model of brevity, but the density is justified by the tool's complexity and the need to communicate all the interpretation rules.

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 tool with this many behavioral caveats, the description covers all critical interpretation rules, including null pressure reasons, partial windows, and omitted price-coverage fields. The presence of an output schema handles return structure, so the description's focus on semantics makes it contextually complete for an AI agent.

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 input schema fully covers all three parameters with 100% description coverage, so the baseline is 3. The tool description adds no specific parameter syntax beyond noting the 7-day default/keyless access, so it does not further elevate the score.

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 clearly identifies this as a single call that returns the complete whale picture for one coin, enumerating the data categories (flow windows, venue splits, pressure state). Although it lacks an imperative verb like 'get' or 'list', the phrasing 'Everything the recorded whale record can say about ONE coin' is a specific purpose statement and distinguishes it from sibling tools by scope and comprehensiveness.

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?

The description does not explicitly name alternative tools or exclusion conditions, but it establishes a clear context: use this for a comprehensive single-coin profile. It also notes access limitations (keyless 7-day window, developer plan reaches 30 days) and that it provides descriptive market data only, giving clear context even without direct comparison to siblings.

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 description's 'Descriptive market data only' reinforces but does not significantly extend the safety profile. It adds context about time windows, which is useful behavioral information, but does not describe edge cases (e.g., empty results) or data source specifics.

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?

The description is two sentences long, front-loaded with the purpose, and every phrase adds value. 'Descriptive market data only' is a concise qualifier that prevents misinterpretation. No wasted words.

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?

Given the simplicity of the tool (no parameters) and the existence of an output schema, the description provides sufficient context: it conveys the data type (the output schema will handle return values), the time windows, and the 'descriptive only' limitation. It doesn't explain what 'unusual' means or how it's calculated, but that is reasonable for a radar-style overview 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 tool has zero parameters, so the description does not need to explain any parameter semantics. The mention of 1h/4h/24h windows appears to be output-related rather than input parameters, which is acceptable given the empty schema and baseline of 4 for parameterless tools.

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 clearly states the tool's function: identifying coins with unusual whale flow across 1h, 4h, and 24h windows. This distinguishes it from sibling tools like whale_flow or whale_trades by focusing on 'unusual' flow rather than raw data, though it lacks an explicit verb like 'lists' or 'detects'.

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?

No explicit guidance is given on when to use this tool versus alternatives. The phrase 'right now' implies real-time usage, but there is no mention of when not to use it, what other tools it complements, or any exclusions. The 'Descriptive market data only' note hints at limitations but is not a clear usage guideline.

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?

The description adds substantial behavior beyond the readOnly/idempotent annotations: free vs paid shape differences (BTC/USD only, 15-min delays, $250K DEX threshold), row caps (50 vs 500), pagination notes (deeper pages on REST API), and the 'capped'/'scan_capped' indicators in payload/params. It also states 'Descriptive market data only', clarifying non-actionable nature.

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?

The description is two sentences, but the second sentence is dense yet information-rich, covering plans, limits, and shape details. Every part contributes valuable context, though the length and density slightly reduce scannability compared to a shorter alternative. No fluff, but the sentence could be broken for readability.

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?

Given the tool's complexity (5 params, output schema, annotations), the description is complete: it identifies the alias relationship, provides usage guidance, details access-tier behavior, and mentions pagination limitations. It also notes that this is descriptive data only, and the output schema covers return values, so no further explanation is needed.

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 baseline is 3. The tool description adds context about row caps and access tiers, which supports understanding of `limit` and `min_usd`, but it doesn't add per-parameter semantics beyond what the schema already provides.

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 clearly states the tool is a deprecated alias for whale_trades and describes its functionality: 'Live whale trades merged across 15 CEX venues plus on-chain DEX swaps (Ethereum, Base, Arbitrum), newest first.' This is a specific verb+resource with explicit distinction from sibling tools by labeling it an alias and directing users to prefer whale_trades.

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 'Deprecated alias for whale_trades, kept so existing clients keep working. Prefer whale_trades.' This gives clear when-to-use and alternative guidance. Additionally, it details when keyless vs paid limits apply, helping users decide whether to use this tool for low-volume vs high-volume needs.

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?

Despite annotations already indicating read-only and idempotent behavior, the description adds substantial detail about rate limits (50 rows keyless, 500 paid), delayed data for non-BTC pairs, minimum trade thresholds for DEX swaps, and the 'capped' signal. It also disclaims 'Descriptive market data only.' No contradiction with annotations.

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?

The description is three sentences, with the core function in the first sentence, plan limitations in the second, and a clear disclaimer in the third. Every sentence adds value, and the information is well-structured and 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?

Given the tool has an output schema and strong annotations, the description covers the essential context: data sources, ordering, plan-based limitations, and the read-only nature. It does not explicitly address pagination behavior beyond row caps, but the schema's 'capped' description covers that. Overall, it is sufficiently complete for a complex 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?

All five parameters have descriptions in the schema, so baseline is 3. The tool description adds some context about the 'free shape' and row caps that relate to parameters, but most of this is repeated in the schema (e.g., limit cap, DEX swap threshold). It does not significantly enhance parameter understanding beyond the schema.

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 clearly states the tool aggregates live whale trades from 15 CEX venues plus DEX swaps on three chains, with newest first. While the scope is specific, it does not explicitly differentiate from sibling tools like whale_tape or onchain_whales, so it falls short of a 5.

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?

The description provides context about free vs paid plan limitations and data delays, which implies when it might be useful, but it does not explicitly state when to use this tool over alternatives like onchain_whales or whale_radar. No exclusions or alternative recommendations are given.

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