Crypto Derivatives Data: Perp Funding Rates, Open Interest, Basis, IV

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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the full payment contract: $0.005 per successful call, USDC on Base via x402, payment passed in _meta['x402/payment'], free on bad input, uncharged under 3 venues. It also enumerates what the response contains and scopes it as read-only data ('Data only'), which the annotations alone would not convey as concretely.

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?

Front-loads the snapshot content before the venue list and billing details, so the most decision-relevant information comes first. Slightly padded by promotional phrasing ('The derivatives data bundle for trading agents on BTC, ETH, SOL and more') and a long payment sentence, but nothing is redundant.

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 one-parameter, no-output-schema tool, the description covers what is returned, which venues are covered, that it is data-only, and the complete payment/error-billing contract. An agent has everything needed to decide to call it and to construct a paid request.

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 the single 'coin' parameter is fully documented in the schema with alias examples (BTCUSDT, BTC-PERP, XBT, 1000PEPE, kPEPE). The description only repeats the 'one coin' constraint and lists a few example symbols, adding no format or normalization rules 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?

Names a specific resource (crypto derivatives snapshot) with explicit scope ('one coin in one call') and enumerates the contents: funding rates, predicted funding, OI per venue, perp premium, futures basis, liquidations, long/short ratio. This implicitly distinguishes it from the single-metric siblings (open_interest, liquidations, futures_basis, perp_funding_rates), though it never names them directly.

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?

Usage is only implied via 'The derivatives data bundle for trading agents' — the agent must infer that this is the aggregate alternative to the narrower sibling tools rather than calling five of them. There is no explicit when-to-use/when-not statement, and the only stated conditions are billing ones ('Bad input is free; under 3 venues not charged').

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?

Goes well beyond the readOnly/openWorld/idempotent annotations: discloses exact pricing ($0.005 per successful call, x402 USDC on Base payment via _meta), billing edge cases (bad input free, under 3 venues not charged, empty results still charged), and a data-only disclaimer. An agent knows cost, failure economics and payment mechanics before invoking.

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?

Front-loads purpose and scope before the pricing/payment sentence. Dense but nearly every clause carries information; the exchange list is long but justified for a cross-venue scanner. Slight density tax keeps it from a 5.

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

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

No output schema exists, yet the description enumerates the returned fields (spread, venues, rates, gross/net APR, breakeven days) and the liquidity filter, and covers pricing and payment. An agent has everything needed to call and interpret results.

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 baseline is 3, but the description adds value by linking params to outcomes: the 24h volume liquidity filter, fee-adjusted net APR and breakeven days (relating to fee_pct and holding_days). It doesn't restate defaults or ranges, so it stops short of a 5.

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

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

States a specific verb and resource ('Funding arbitrage scanner') plus concrete scope: 8 named exchanges, every coin, widest cross-venue perp funding spread. Outputs listed (long/short venue, both rates, net APR, breakeven days) make it readily distinguishable from siblings like funding_rate_history and perp_funding_rates.

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

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

Gives use-case context ('Funding rate arbitrage, basis trade and carry screening of perpetual swaps') and a liquidity filter condition, implying when to reach for it. However it never names alternatives such as perp_funding_rates or perp_screener, nor states when-not to use it, so routing is left to inference.

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=true and openWorldHint=true annotations, the description discloses the 30-day cap, the billing model ($0.003 per successful call over x402 USDC on Base), where the payment goes (_meta["x402/payment"]), and the failure semantics (bad input free, a failing venue not charged). Those billing and error-behavior details are exactly the kind of context annotations cannot carry, and nothing contradicts the declared hints.

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 payload (scope, return fields, use case, pricing/failure terms) is front-loaded into the first two sentences, with payment mechanics trailing. It is dense but every clause carries information; only the venue parenthetical slightly duplicates the enum.

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?

There is no output schema, and the description compensates by enumerating the return payload (per-print interval, 8h rate, APR, plus avg/min/max/% positive and the covered window). Combined with pricing, error handling, and scope limits, an agent has everything needed to call this correctly and understand the cost.

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 the venue enum, coin aliases, and the 1-30 day range with a default of 7 all documented in the schema, so the baseline is 3. The description restates the 30-day limit and the seven venues but adds no interpretation of the parameters beyond that, so it neither compensates for nor improves on 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 names a specific verb and resource (funding rate history) and pins the scope tightly: one coin, one exchange, up to 30 days, with the venue enum spelled out. It implicitly separates itself from snapshot-style siblings like perp_funding_rates by stressing 'historical' and 'one coin, one venue', but it never names an alternative, so the differentiation is inferred rather than stated.

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 concrete use cases ('backtests and carry studies') and a clear boundary ('one coin, one exchange, up to 30 days'), which is enough context to know when this tool fits. It stops short of telling the agent when NOT to use it or which sibling (e.g. perp_funding_rates for live rates, funding_arbitrage_scan for cross-venue work) to pick instead.

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 openWorldHint=true, and the description adds genuinely non-obvious behavior: it is data-only, bad input is free, calls resolving under 2 venues are not charged, and payment is required via x402 in _meta['x402/payment'] at $0.003 per successful call. That payment/auth requirement is critical context an agent cannot get from annotations or schema. It stops short of describing response shape or rate limits.

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

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

The core purpose is front-loaded, but the body is a long run-on sentence mixing venues, metrics, keyword-like filler ('Crypto futures basis for BTC, ETH and more') and pricing. The keyword line and the redundant restatement of scope do not earn their 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?

For a one-parameter, read-only tool with no output schema, the description is largely complete: it enumerates the metrics returned and the venue set, and discloses the payment model. Only the response structure and per-venue failure behavior remain unspecified, which is a minor 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?

Schema coverage is 100% and the coin parameter already documents accepted aliases (BTCUSDT, XBT, 1000PEPE, kPEPE). The description only reinforces the single-coin scope, adding no format or normalization detail beyond the schema, so the baseline 3 applies.

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

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

The description states a specific resource and scope: futures basis and term structure for one coin, covering dated futures across named venues with days to expiry, basis vs index and annualised basis, plus perp premium and predicted funding. It clearly distinguishes itself from the screener/scan siblings by the 'one coin' scope, though it never names those siblings explicitly.

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?

Usage is only implied: 'one coin' signals a per-coin lookup rather than a market-wide scan, and the pricing note ('under 2 venues not charged') hints at thin-data outcomes. There is no explicit statement of when to choose this over derivatives_snapshot or perp_funding_rates, which cover overlapping territory.

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?

Goes well beyond the readOnly/openWorld annotations with genuinely load-bearing behavior: 'Data only', an explicit price point, the x402/USDC-on-Base payment channel and the exact _meta["x402/payment"] key, and a clear failure-mode policy ('bad input is free; nothing is charged when no venue answers'). For a paid tool with no output schema this is exactly the disclosure an agent needs before calling.

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?

Front-loaded with purpose and data fields, then operational concerns (pricing, payment, free-on-failure) — no filler sentences. The first sentence is a dense semicolon-chained run-on that is harder to scan than it needs to be, which costs it the top score.

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 2-parameter read tool with no output schema, the description covers everything an agent needs: what is returned, what the optional parameter changes, cost and payment mechanics, and failure-mode billing. Nothing material is left to guesswork.

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 schema fully documents both fields; the description adds meaning by stating what 'expiry' unlocks (that expiry plus its chain with each venue's greeks). Minor deduction: it scopes the tool to 'BTC and ETH options' while the schema advertises SOL, PEPE and aliases, leaving the agent slightly unsure of the supported universe.

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?

Names a specific resource (crypto options IV per expiry) and enumerates the exact measures returned: ATM IV, 25-delta skew, put/call OI ratio, max pain, DVOL, plus per-strike chains with greeks. The options/expiry framing cleanly separates it from the perp- and futures-oriented siblings (perp_funding_rates, futures_basis, open_interest) without needing to name them.

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?

Usage is only implied: 'Volatility surface inputs for BTC and ETH options' suggests a modeling use case, and 'with an expiry, the options chain per strike' tells the agent what the optional parameter unlocks. There is no explicit when-to-use-this-vs-a-sibling guidance and no statement of exclusions (e.g. that perp IV/term structure lives elsewhere).

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?

Adds substantially beyond the annotations: the data is read-only but metered, at $0.003 per successful call via x402 USDC-on-Base payment passed in _meta, with bad input and sub-2-feed responses free. It also discloses upstream feed coverage gaps, which the annotations (readOnly/openWorld/idempotent=false) cannot convey.

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?

Front-loaded with the core verb and resource, with the price/payment mechanics last, which is the right ordering. It is dense and somewhat run-on, and the clause 'Liquidation data for BTC, ETH, SOL and more' partly repeats the coin parameter, but no sentence is wasted.

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

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

With no output schema, the description compensates by sketching the return shape (per-venue long/short USD, totals, largest events) and by covering cost, payment mechanism, billing edge cases and coverage limits. An agent has everything needed to decide and invoke 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 coverage is 100%, so both the coin symbol formats and the 1-24 default-24 window are fully documented in the schema. The description only restates the coin universe (BTC, ETH, SOL) and the hour range, adding no syntax or edge-case guidance beyond the structured fields, 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?

States a specific resource (perpetual-futures liquidations for one coin), the exact measures returned (long/short liquidations in USD per venue, totals, largest events) and the time window. Names the covered venues (Gate, Bitfinex, dYdX, Deribit, OKX) and the non-covered ones, which no sibling tool does, so it is unmistakable against derivatives_snapshot or open_interest.

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

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

Gives clear operative context: one coin at a time, 1-24h look-back, and an explicit coverage exclusion list (Bybit, Hyperliquid, Kraken are WebSocket-only and not serviced) that tells the agent when the tool will fail. It does not point to any alternative sibling for related derivatives metrics, so it falls short of a full when/when-not/alternatives statement.

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 the safety profile (readOnly, openWorld, non-idempotent), and the description goes further with genuinely non-obvious operational facts: $0.003 per successful call billed via x402 USDC on Base through _meta["x402/payment"], bad input is free, and calls resolving under 2 venues (3 for a coin listed on 3+) are not charged. It doesn't discuss rate limits or what an error response looks like, so it stops short of a 5.

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

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

Purpose comes first, then coverage and returned fields, then cost/payment mechanics last. The venue list and change windows each carry information an agent needs; the pricing clauses are short and load-bearing rather than padding.

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?

There is no output schema, and the description compensates by specifying the per-venue and aggregate values returned and the three change horizons. Payment/auth requirements and billing edge cases are also disclosed, leaving nothing essential for a correct call unstated.

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

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

Schema description coverage is 100% and the schema already documents alias handling (BTCUSDT, BTC-PERP, XBT, 1000PEPE, kPEPE) plus length bounds. The description adds only the constraint that exactly one coin is queried at a time, which is slight but real value over the schema, 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 first clause names the exact resource and scope: open interest of one coin's perpetual futures, broken out per exchange. It enumerates the venues and the returned metrics (per-venue OI in coins and USD, share, total, 1h/4h/24h change), which cleanly separates it from siblings like perp_funding_rates, futures_basis, or perp_screener.

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 coin' framing implies this is the single-symbol lookup versus the multi-coin screening siblings, but that routing is left to inference. There is no explicit statement of when to prefer this over derivatives_snapshot or perp_screener, and no 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 cover read-safety, but the description adds genuinely non-structured context: payment is required via x402 (USDC on Base) passed in _meta["x402/payment"], the price is $0.003 per successful call, bad input is free, and calls touching fewer than two venues are not charged. This is exactly the auth/payment/cost surface an agent cannot infer from 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 core capability and venue list are front-loaded and nearly every clause carries information. The opening sentence is dense and run-on, and the 'L2 orderbook liquidity for BTC, ETH, SOL and more' clause partially repeats the coin parameter example, keeping it just short of a 5.

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

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

With no output schema, the description carries the return-value burden and does so thoroughly by enumerating every returned metric. Combined with billing and payment details, an agent has everything needed to call it correctly and understand the cost before invoking.

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 coin/levels/size_usd are already fully documented, including example symbols. The description mentions 'estimated slippage for your order size' and 'top N levels' but adds no format or default detail beyond the schema, so the baseline 3 applies.

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

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

States a specific verb+resource ('Order book depth of one coin's perpetual') and enumerates eight named venues plus the exact metrics returned (best bid/ask, spread bps, depth in USD within 0.1/0.5/1/2% of mid, imbalance, slippage, walls). None of the siblings (funding, OI, liquidations, basis) overlap, so an agent can route to it unambiguously.

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?

Usage is implied by the returned metrics: an agent wanting spread/depth/slippage for a single coin on multiple perp venues will infer this is the tool. However, no sibling is named as an alternative and no explicit when-not guidance is given; billing rules ('bad input is free', 'under 2 venues not charged') describe cost, not selection criteria.

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 goes far beyond annotations by detailing the specific metrics returned (interval, APR, mark, index) and disclosing complex operational behaviors like including predictions via Hyperliquid and the mandatory pricing model/payment requirements.

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?

While very detailed, the description front-loads the core value proposition (8 exchanges, funding rates) immediately. The length is justified by the necessary level of technical and operational detail required for accurate tool usage.

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 and the lack of an output schema, the description is highly complete. It covers the domain knowledge (what the data represents), the operational constraints (pricing), and the technical scope (8 venues), leaving no ambiguity for the 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 is sparse, only requiring a 'coin' string. The description significantly enhances semantics by providing explicit examples of valid formats (BTCUSDT, BTC-PERP, 1000PEPE, XBT), which are critical for correct parameter invocation.

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 purpose (providing funding rates for perpetual futures) and distinguishes itself by specifying the comprehensive coverage across 8 distinct exchanges, differentiating it from more general or historical funding rate 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?

It clearly defines the context for use (multi-exchange, per-coin data) and lists the types of coins supported (BTC, ETH, SOL), making it easy for an agent to determine if its query fits this tool's scope.

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 the safety profile (readOnlyHint, openWorldHint), but the description adds substantive behavior the annotations cannot: per-call pricing ($0.005 per successful call), the x402/USDC-on-Base payment channel passed via _meta["x402/payment"], and non-obvious billing rules (bad input free, under 3 venues not charged, empty results still charged). That billing asymmetry is exactly the kind of detail an agent needs before retrying a filter that returns nothing.

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 scoping and pricing information is front-loaded and useful, but the second sentence ('A funding screener and perpetuals market ranking for BTC, ETH, SOL and hundreds of altcoins') is keyword-stuffed marketing that duplicates the first sentence's content without adding selection signal.

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

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

With no output schema, the description at least implies the return shape by naming the metrics the results are sorted by, and it covers cost, payment mechanics and charge conditions. The only real gap is that it never states the result record shape or whether venues are merged per coin, but for a 4-param read-only screener this is close to 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?

Schema description coverage is 100%, so defaults, ranges and enum values are already fully documented in the schema. The description restates the sort dimensions and the high/low funding ordering but adds no syntax or format detail beyond that, 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 states a specific resource (every perpetual future across Bybit, Hyperliquid, dYdX, Gate, Kraken, Bitfinex, Deribit and OKX) and the exact sort dimensions (funding APR, OI, 24h volume, 24h change). The 'in one call' cross-venue framing implicitly separates it from single-metric siblings like open_interest or perp_funding_rates, though no sibling is named explicitly.

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?

Usage is only implied through the sort/order semantics and the mention of 'highest and lowest funding views'. Nothing tells the agent when to pick this over perp_funding_rates, derivatives_snapshot or funding_arbitrage_scan, and there are no stated exclusions or prerequisites.

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