Server Quality Checklist

Tool Scores

• flag_outcomesB
  3.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral context: data is 'logged live and never backfilled', indicating freshness and lack of historical coverage. It also clarifies that this is descriptive market data only, setting expectations about the level of insight. This goes beyond the annotations without contradiction.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

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

  The description is concise, two sentences, and front-loads the core content. The inclusion of a tracking link adds a marketing element but does not bloat the description. It is efficient and does not waste words, though the URL is not strictly necessary for understanding the tool.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has no output schema and minimal parameter docs, so the description carries the burden of explaining what is returned. It mentions fire-time and later prices, giving some return shape, but it omits details about pagination (limit), filtering (coin/type), or the meaning of 'hours'. Key contextual gaps remain, making the description only minimally adequate.

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

  Parameters1/5

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

  Schema description coverage is 0% for 4 parameters (coin, type, hours, limit), and the description does not explain any of them. The term 'type' is especially ambiguous, and there is no guidance on how to filter or interpret the time window. Since the description must compensate for the lack of schema documentation, it completely fails to do so.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly indicates the tool returns recently fired signal-ledger flags with fire-time and later prices, which is a specific resource. It distinguishes from siblings by focusing on signal outcomes rather than whale trades or liquidations. However, it lacks an explicit verb like 'list' or 'get', making it a noun phrase rather than a direct action statement.

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

  Usage Guidelines3/5

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

  The description implies usage context by stating 'Descriptive market data only' and offering 'More depth on a developer plan', which suggests this is a basic, read-only view and that deeper data is not available here. It does not explicitly name alternatives or provide clear when-to-use versus when-not-to-use guidance, but the limitation is somewhat conveyed.

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

• liquidationsB
  3.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds useful behavioral context by clarifying that event counts vs dollar amounts are separate, and that sell-side events correspond to long liquidations. 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.

  Conciseness3/5

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

  The description is mostly concise, with three sentences of useful content followed by a promotional link. The marketing sentence ('More depth on a developer plan') does not earn its place for an agent selecting a tool, making the structure slightly cluttered.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the simple tool (2 params, no output schema), the description covers the main output semantics (counts vs USD) but leaves gaps: no explanation of the 'pair' parameter format, no mention of 'limit', and no return value structure. It is adequate but not fully complete.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate for explaining parameters. It mentions 'pair' conceptually, but does not explain the format or expected values. The 'limit' parameter is not mentioned at all, leaving its purpose and constraints unclear.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool provides 'Recent liquidation trades for a pair with the long and short breakdown', which is a specific verb+resource+scope. It explains the meaning of long vs short liquidations, adding clarity. However, it doesn't explicitly differentiate from sibling tools like whale_trades, 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.

  Usage Guidelines3/5

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

  The description implies usage: use this tool for recent liquidation data. It says 'Descriptive market data only', suggesting it's for informational purposes. But it does not provide explicit when-to-use vs alternatives or any exclusions, so guidance is only implied.

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

• whale_radarA
  3.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful context beyond annotations: it specifies time windows (1h, 4h, 24h) and clarifies that the data is 'descriptive market data only', reinforcing the read-only nature. No contradiction is present.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

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

  The description is brief and front-loaded with the tool's purpose. The second sentence includes a promotional link with UTM parameters, which is somewhat extraneous for an agent invocation but does not significantly bloat the text. Overall, it is concise and well-structured.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With no output schema and zero parameters, the description is the sole source of information. It conveys the core functionality and time windows, but it does not clarify the output format, define 'unusual', or differentiate from sibling tools such as whale_flow or whale_trades. This leaves notable gaps for an agent selecting and invoking the tool.

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

  Parameters4/5

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

  The tool takes zero parameters, so the schema fully covers parameter semantics. The description doesn't need to provide additional parameter meaning, and the baseline score of 4 for zero-parameter tools applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies the tool as a radar for coins with unusual whale flow across specific time windows, distinguishing it from siblings like whale_trades and whale_flow. However, it lacks an explicit action verb, relying on the interrogative 'which coins' instead of a direct verb like 'list' or 'get'.

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

  Usage Guidelines2/5

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

  The description provides no explicit guidance on when to use this tool versus alternatives. 'Descriptive market data only' is a limitation, not a usage directive, and there is no mention of exclusions or alternative tools. The agent is left to infer usage from the tool's name and title.

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

• market_overviewA
  3.6/5.0
  Behavior4/5

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

  Annotations already establish readOnlyHint, idempotentHint, and non-destructive operation. The description adds useful behavioral context: it is descriptive only (no predictions), and passing a coin returns a single row without paging. This goes beyond the annotations to help the agent understand how the tool behaves.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

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

  The description is three sentences plus a link. It front-loads the main purpose and includes the key parameter note. The developer-plan URL is extra but not disruptive. It is reasonably concise with no repeated information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has 2 parameters, no output schema, and only basic annotations. The description lists the data categories returned (totals, whale net flow, BTC regime, top rows) and explains the coin parameter. However, it doesn't describe the response format (e.g., object vs array) or the limit parameter, so an agent might lack full clarity on how to use it correctly.

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

  Parameters3/5

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

  The description explains the 'coin' parameter: passing it returns one symbol's row directly without paging. However, the 'limit' parameter is not described at all, and with 0% schema coverage, the description only partially compensates for the schema's silent parameters. It does not clarify what limit controls (e.g., number of top rows).

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool is a one-call market scan that returns totals (volume, OI, liquidations, mcap), 24h whale net flow, BTC risk regime, and top rows by volume. This gives a specific verb (scan) and resource (market data). However, it does not explicitly differentiate from sibling tools like market_snapshot or whale_flow, so it misses the top tier of distinguishing use cases.

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

  Usage Guidelines3/5

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

  The description implies this is the go-to for a broad market overview ('One-call market scan') and explains the coin parameter usage. It also notes 'Descriptive market data only' and points to a developer plan for more depth, but it doesn't explicitly say when to use this tool instead of siblings like whale_flow or liquidations. This is implied rather than explicit.

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

• market_snapshotA
  3.7/5.0
  Behavior4/5

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

  Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds valuable context by specifying 'Descriptive market data only' and explaining access tiers (keyless free pairs vs. paid plan for all pairs), which goes beyond the annotation hints.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

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

  The description is three sentences and front-loaded with the core purpose. It is efficient, though the embedded developer plan URL adds minor noise and could be considered promotional rather than essential for tool invocation.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple one-parameter tool, the description covers the data returned and access restrictions. However, it lacks the pair format and any indication of the output shape (no output schema), leaving minor but important gaps for correct usage.

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

  Parameters2/5

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

  The schema has 0% description coverage for the only parameter 'pair'. The description mentions 'for a pair' but provides no format, examples, or whether it is required (required count is 0), leaving the agent unsure how to populate the pair parameter correctly.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: 'One-call market state for a pair' with specific data fields (last price, 24h stats, funding rate, open interest, liquidations) across 15 exchanges. This distinguishes it from siblings like market_history or market_overview by emphasizing a comprehensive current snapshot.

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

  Usage Guidelines3/5

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

  Usage context is implied via 'One-call market state' suggesting a quick snapshot, and the description notes keyless versus paid plan access. However, it does not explicitly compare against alternative tools (e.g., market_history for historical data) or state 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.

• whale_flowA
  3.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered. The description adds useful behavioral context: it is 'descriptive market data only,' limited to one coin, and covers a rolling window. This provides depth beyond the annotations without contradiction.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The first sentence is concise and information-dense, effectively describing the tool. However, the second sentence is promotional (pointing to a developer plan) and does not aid tool invocation, adding unnecessary noise. It could be restructured to remove the marketing content.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With no output schema and minimal schema descriptions, the description provides the core concept but omits critical operational details: how to format the coin parameter, what exactly 'hours' controls, and what happens if omitted (since only coin is required). An agent would likely need to guess or infer parameter semantics.

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

  Parameters2/5

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

  Schema coverage is 0% — no parameter descriptions exist. The description hints at 'coin' (one coin) and 'rolling window' (likely tied to 'hours'), but does not explicitly explain the format, units, or default behavior of the 'hours' parameter. This is ambiguous for an agent constructing a call.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: 'Hourly buy and sell USD flow buckets for one coin, CEX and DEX split, over a rolling window.' This is a specific verb+resource combination that distinguishes it from sibling tools like whale_trades or whale_radar by emphasizing the aggregated, time-bucketed nature.

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

  Usage Guidelines4/5

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

  The description implies usage context: it is for one coin's daily flow overview and is 'descriptive market data only.' However, it does not explicitly mention when to use this versus alternatives like whale_trades or whale_tape, nor does it provide exclusion criteria. The context is clear but lacks explicit alternative naming.

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

• crypto_newsA
  3.8/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveness=false, so the description need not repeat those. It adds context that the sentiment score is 'pre-computed' and that data is 'descriptive', but does not disclose behaviors like default behavior when 'coin' is omitted, response structure, rate limits, or what 'macro picture' entails. Some value beyond annotations is present, but not a rich behavioral profile.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

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

  The description is two sentences, with the core purpose front-loaded. The first sentence is information-dense, covering headlines, sentiment range, and scope. The second sentence adds a caveat and a promotional URL, which slightly dilutes focus but does not introduce fluff. Overall, it is appropriately concise.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with one optional parameter and no output schema, the description explains the input (coin) and the general output (headlines + sentiment + macro picture) but does not detail the exact return structure, fields, or behavior when 'coin' is omitted. It also leaves 'macro picture' undefined. While not overly complex, the lack of output schema increases the need for description to clarify output, which is only partially met.

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

  Parameters4/5

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

  The schema's 'coin' parameter has no description (0% coverage), so the description must compensate. It does so by stating the tool returns data 'for one coin', clearly indicating the parameter identifies the cryptocurrency of interest. It also explains the sentiment score range. This adds meaningful semantics, though it does not specify accepted value formats (e.g., symbol vs. name) or the effect of omitting the parameter.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool provides 'Recent crypto headlines with a pre-computed sentiment score (-100 to +100)' for a specific coin plus a macro picture. This is a specific verb+resource (headlines/sentiment) and differentiates from sibling market-data tools by focusing on news and sentiment rather than trades or price data.

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

  Usage Guidelines3/5

  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 for informational/news purposes, not for live trading data. It does not explicitly state when to use this tool over siblings (e.g., whale_trades, market_snapshot) nor does it provide exclusions. The optional 'coin' parameter suggests single-coin queries, but usage context remains largely implicit.

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

• funding_matrixA
  3.8/5.0
  Behavior4/5

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

  Annotations already mark this as read-only, idempotent, and non-destructive. The description adds meaningful context: keyless access, descriptive-only data, and a developer-plan depth limitation. This goes beyond the annotations without contradicting them, giving the agent a clearer picture of access and data constraints.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

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

  The description is compact and front-loaded with the core purpose, followed by useful access and limitation notes. The developer-plan URL is a minor addition but provides relevant upgrade context. No redundant or vague filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple single-parameter tool with no output schema, the description covers purpose, data nature, keyless access, and venue-dependent payout time. It could mention output shape or error handling, but the provided context is largely sufficient for an agent to understand the tool's role.

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

  Parameters2/5

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

  With only one 'pair' parameter and 0% schema description coverage, the description mentions 'one pair' but does not clarify the expected format, whether the parameter is required (schema lists no required params), or what happens when omitted. This is a notable gap for the agent to correctly invoke the tool.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states that the tool provides per-venue funding rates for one pair, including predicted next rate and payout time when available. It identifies the resource (funding rates) and distinguishes it from sibling tools focused on whales, liquidations, and market snapshots, though it lacks an explicit verb like 'get' or 'list'.

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

  Usage Guidelines4/5

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

  The description gives useful context by noting it is keyless on any streamed pair and descriptive market data only, signaling read-only usage. It does not explicitly name alternative tools or provide when-not-to-use guidance, but the scope is clear enough for an agent to select it for funding-rate needs.

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

• liq_zonesA
  3.8/5.0
  Behavior5/5

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

  Beyond the readOnly and idempotent annotations, the description discloses that data is modeled from leverage assumptions, is a projection rather than executed trades, and that the snapshot depth varies by plan (free vs developer). It also notes this is descriptive market data only, adding meaningful behavioral context.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The main purpose is front-loaded in the first sentence, but the description includes promotional URL with UTM parameters and a somewhat redundant 'Descriptive market data only' clause. It is not overly long, but the URL and plan-upgrade marketing could be trimmed without losing essential tool guidance.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has a simple one-parameter schema and no output schema, so the description carries the burden of explaining return values. It clarifies the data is a projection and varies by plan, but does not describe what fields the 'level book' contains (e.g., price levels, quantities, timestamps), leaving part of the response format to guesswork.

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

  Parameters2/5

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

  The schema provides only a 'pair' property with no description or format hints. The description mentions 'one pair' but does not explain expected format (e.g., 'BTCUSD' vs 'btc_usd'), default behavior, or supported pairs. With 0% schema coverage, the description fails to compensate for the missing parameter details.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies the tool as a projected liquidation level book for one pair, and explicitly distinguishes it from executed trades. This differentiates it from the sibling 'liquidations' tool, which likely shows actual liquidation events.

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

  Usage Guidelines3/5

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

  The description implies use for viewing projected liquidation levels and notes plan-based access differences, but it does not explicitly state when to prefer this over alternatives like 'liquidations' or 'market_snapshot'. No direct when-not or alternative guidance is provided.

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

• squeeze_scoreA
  3.8/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context: it emphasizes 'Descriptive market data only,' requires a paid plan, and lists the specific inputs used to compute the score. 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.

  Conciseness3/5

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

  The first sentence is informative and front-loaded, but the description contains redundancy: 'Descriptive, not a trade signal' and 'Descriptive market data only' say the same thing, and the developer plan is mentioned twice. It could be tightened without losing meaning.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description explains what the score is composed of and that it is descriptive, but with no output schema, it does not fully describe the return value (e.g., structure of the score and overexposed side). It also leaves the behavior of optional pair parameter ambiguous. This is a simple tool, but the description could round out operational details.

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

  Parameters2/5

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

  Schema coverage is 0% and there is only one parameter, 'pair.' The description says 'per pair' but does not specify the expected format (e.g., 'BTCUSD' vs. 'BTC/USD') or behavior when omitted (e.g., return all pairs). While the param name is self-explanatory, the description adds minimal value beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool produces a fused 0-100 crowding score per pair, enumerates the input components (funding, long/short accounts, taker imbalance, OI trend), and notes the overexposed side. This distinguishes it from sibling tools like whale_trades or market_snapshot by its synthetic scoring nature.

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

  Usage Guidelines4/5

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

  The description explicitly says 'Descriptive, not a trade signal,' which provides clear guidance on when to use it (information) vs. when not to (trading decisions). It also mentions the paid developer plan requirement. However, it does not name alternative tools or explicitly contrast with siblings, so it stops short of full exclusion guidance.

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

• whale_tradesA
  3.8/5.0
  Behavior5/5

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

  The description goes far beyond the annotations by disclosing row cap, ordering, free vs. paid plan limits (BTC/USD only, 15-min delays, $250K+ DEX swaps), and that it is descriptive only. This provides operational details the annotations (readOnlyHint, idempotentHint) do not cover, and is consistent with them.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The description has a clear first sentence but then becomes redundant, repeating paid-plan details ('a paid developer plan lifts...' and 'More depth on a developer plan') and includes a promotional URL with tracking parameters. This takes space away from more essential parameter clarification without adding new value.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Providing good context on data shape, delays, tier limitations, and row cap is helpful, but the lack of return-value details (no output schema) and missing parameter mappings leaves the agent with uncertainty about how to invoke the tool for specific filtering (coin, min_usd, source). The description is adequate the high-level purpose but incomplete for precise usage.

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

  Parameters2/5

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

  Schema coverage is 0%, and the description does not name or explain any of the parameters (coin, limit, source, min_usd). While it hints at limit ('capped at 50 rows'), source ('CEX/DEX'), and min_usd ($1M+, $250K+), these are indirect and coin is entirely unaddressed. The description fails to compensate for the missing schema descriptions.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description names a specific verb and resource: 'Live whale trades merged across 15 CEX venues plus on-chain DEX swaps,' with clear scope (venues, blockchains) and output constraints ('newest first, capped at 50 rows'). This distinguishes it from sibling tools like whale_tape or whale_radar by highlighting the aggregated multi-venue, multi-chain nature.

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

  Usage Guidelines3/5

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

  The description implies usage (a quick merged feed of whale trades) and notes limitations ('capped at 50 rows', 'full depth on the REST API'), but it never explicitly contrasts with sibling tools or states when to choose this over alternatives. No exclusions or alternative tool names are given, so guidance is only implicit.

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

• market_screenerA
  4/5.0
  Behavior4/5

  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 that data is 'descriptive' only and explains that bands are relative to each pair's own recorded days and whale flow is relative to the coin's own average—important behavioral nuances beyond what annotations provide.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

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

  The description is concise: three sentences with the core purpose front-loaded. The first sentence is dense but packs essential filter semantics. The final sentence with a developer-plan URL is somewhat promotional but not overly verbose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With 6 parameters and no output schema, the description does a decent job explaining filter semantics but lacks return value details, default behavior, and the meaning of limit and compact. Given the tool's complexity, it is adequate for a high-level understanding but not fully complete for correct invocation without additional assumptions.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description must compensate. It explains funding_band/oi_band values (record high, top 5%, etc.) and whale_mult_min relative to the coin's average, and unusual_only as radar-unusual, but it omits the limit and compact parameters entirely, leaving those without meaning.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool screens every recorded pair in one call, with specific filters (funding_band, oi_band, whale_mult_min, unusual_only). It is explicitly labeled 'The discovery call,' which distinguishes it from sibling tools like market_snapshot 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.

  Usage Guidelines4/5

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

  The phrase 'The discovery call' implies it is intended for initial broad market screening across all pairs. It gives context for when to use it but does not explicitly mention alternatives or when not to use it, despite clear positioning among siblings.

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

• market_historyA
  4.2/5.0
  Behavior4/5

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

  Annotations already mark the tool read-only, idempotent, and non-destructive. The description adds valuable context: archive start dates, 30-day keyless limit, and paid plan depth. 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.

  Conciseness5/5

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

  Four tightly written sentences, front-loaded with data categories and archive dates. The developer plan link is brief and relevant to depth limitations, with no filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the absence of an output schema and only three parameters, the description covers the essential context: data types, archive availability, access limits, and read-only nature. It does not detail output format or error conditions but remains sufficient for an 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.

  Parameters3/5

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

  Schema has 0% description coverage and no parameter docs. The description compensates by explaining 'one pair' vs 'one coin' and implying the 'days' parameter, but it lacks explicit parameter formats, requiredness/exclusivity, and valid value guidance.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies a daily history tool with two specific modes: pair-level metrics (funding rate, open interest, price, liquidation totals) and coin-level whale flow. It distinguishes itself from siblings like market_snapshot and whale_flow by emphasizing 'daily history' and archive depth.

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

  Usage Guidelines4/5

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

  Provides clear usage context: keyless calls cover 30 days, paid developer plan reaches full archive, and data is descriptive only. It does not explicitly exclude alternative tools or state when to prefer this over siblings, but the scope is well implied.

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

• market_extremesA
  4.3/5.0
  Behavior4/5

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

  Annotations already establish read-only/idempotent behavior; the description adds behavioral detail by specifying 'Descriptive market data only,' that it scans daily across every recorded pair, and that outcome stats are only provided 'where enough events exist.' This goes beyond the structured 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.

  Conciseness4/5

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

  Three sentences, with the core functionality front-loaded in the first sentence and supplementary detail in the second. The third sentence is promotional (developer plan URL) and adds no selection/invocation value, but it is brief and does not significantly hurt readability.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a parameterless data-query tool with no output schema, the description explains what is returned (pairs at record/5% extremes, next-day outcome stats) and how it is computed (relative to each pair's history, across funding/OI/liq). It leaves some details implicit (exact output structure, threshold definitions beyond '5 percent'), but is sufficient for an agent to decide when to call it.

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

  Parameters4/5

  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 per rubric. The schema coverage is 100% and there is nothing for the description to add beyond confirming parameterless operation; the description's scope statement ('Daily scan across every recorded pair') clarifies what the no-parameter call returns.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description opens with a specific question: 'Which pairs sit at a record or in their own top or bottom 5 percent for funding, open interest or liquidations.' It clearly identifies the target metric (extremes relative to a pair's own history) and is distinct from sibling tools like funding_matrix or liquidations by combining those metrics with next-day outcome stats.

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

  Usage Guidelines4/5

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

  It gives clear context: a daily scan across all recorded pairs, and notes it is descriptive market data only, which signals a read-only analytical use case. It does not explicitly name alternative tools or state when not to use it, so it stops 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.

• trade_contextA
  4.3/5.0
  Behavior5/5

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

  Beyond the annotations (readOnlyHint=true, idempotentHint=true), the description adds valuable behavioral context: 'Strictly descriptive: state plus recorded history, no advice' and 'Descriptive market data only.' It also discloses the limitation that certain metrics require a paid plan, and explains the compact mode's token count.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The description is front-loaded with the core purpose and list of contents, but it becomes verbose and redundant. 'Strictly descriptive: state plus recorded history, no advice' and 'Descriptive market data only' say the same thing twice, and the trailing developer-plan URL with UTM parameters is unnecessary for tool invocation.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With no output schema, the description needs to explain the return structure, but it only provides a high-level list of content areas. It does not describe the response format, field names, units, time ranges, or how the non-compact output is organized. The paid-plan caveat is useful, but the absence of output details leaves the agent guessing about the actual result shape.

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

  Parameters4/5

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

  Schema description coverage is 0%, but the description compensates for all three parameters: pair is explained as 'ANY streamed pair keyless', compact is defined as returning a one-line composed answer of about 30 tokens, and position_usd is tied to 'carry arithmetic'. This provides meaningful semantics beyond the bare schema types.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool returns a pre-trade context blob in one call, enumerating the key data points (price, funding, open interest, whale flow, liquidations). This specific verb+resource framing distinguishes it from the specialized sibling tools like whale_trades or liquidations by emphasizing the aggregated, one-call nature.

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

  Usage Guidelines4/5

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

  The phrase 'pre-trade context blob in one call' clearly indicates when to use it: when you need a comprehensive market context before a trade. It notes the compact option for a shorter answer, but does not explicitly say when not to use it or name alternative tools for narrower queries.

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

• whale_tapeA
  4.4/5.0
  Behavior5/5

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

  Beyond the read-only and idempotent annotations, the description discloses critical behavioral details: deprecated status, 15 CEX venues plus DEX swaps on Ethereum/Base/Arbitrum, newest-first ordering, 50-row cap, keyless vs paid plan shape differences (including delays and thresholds), and 'Descriptive market data only.' This substantially enriches the agent's understanding.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

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

  The description is front-loaded with the deprecation warning, which is excellent for quick scanning. However, it becomes a dense run-on paragraph and the promotional URL at the end is not essential for tool invocation, making it slightly less concise than ideal.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool is a deprecated alias, the description covers the key contextual aspects: what data it returns, ordering, row cap, auth tiers, and alternative tools. It does not explain parameter semantics or return structures, but that is partially offset by the deprecation guidance and the annotations.

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

  Parameters2/5

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

  The schema has 0% description coverage and the tool description does not explain any of the four parameters (coin, limit, source, min_usd). It only indirectly references concepts like CEX/DEX and a 50-row cap, but does not state how these map to the schema fields, leaving the agent to guess parameter meanings.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with 'Deprecated alias for whale_trades' which precisely identifies the tool's role as a backward-compatibility proxy. It then elaborates on the underlying data (live whale trades merged across venues) and distinguishes from the preferred sibling whale_trades by explicitly naming it.

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

  Usage Guidelines5/5

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

  'Prefer whale_trades' is a direct, explicit alternative recommendation. It also explains that the alias exists 'so existing clients keep working,' providing clear when-to-use guidance. The note about 'full depth on the REST API' further steers agents toward the right endpoint for more complete data.

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

• whale_contextA
  4.5/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and idempotentHint annotations, the description reveals key behavioral details: it is descriptive market data only, keyless access returns multiples and records but USD magnitudes require a developer plan, and the return shape changes between a flat object and {coins:[...]} depending on input. This gives the agent important context about data fidelity and response structure.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

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

  The description is informative but somewhat dense, packing multiple clauses including a marketing URL. However, each sentence contributes value: the core functionality, input flexibility, output structure, plan limitations, and a link for more depth. It is front-loaded with the main purpose and then details, which is an effective structure.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with one optional parameter and no output schema, the description covers the essential aspects: what the tool does, what metrics it returns, how input affects output shape, and access limitations. It could be more explicit about coin identifier formats or error handling, but it is sufficiently complete for an agent to use effectively.

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

  Parameters4/5

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

  The schema only has an optional 'coin' string with no description. The description compensates by explaining that it accepts a comma-separated list for portfolio briefs and that the return format depends on whether a single coin or list is provided. It does not specify the expected identifier format (e.g., symbol vs. name), but it adds meaningful usage semantics otherwise.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states it compares per-coin whale flow against the coin's own historical average, with specific metrics (multiple of daily average, N-day-high flags, buy share vs 7d). It explicitly calls itself 'The "is this unusual for THIS coin" call,' distinguishing it from sibling tools like whale_flow and whale_radar.

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

  Usage Guidelines4/5

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

  It indicates when to use this tool: when you need to evaluate whether current whale flow is unusual for a specific coin. It also mentions portfolio briefs for comma-separated lists, giving a use case. However, it does not explicitly name alternative tools or state when not to use it, though the contrast with other whale tools is implied.

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