Curade — prediction-market & perp-funding data (x402)

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

With no annotations, the description carries the full burden and does most of it: it discloses data freshness (updated hourly), sourcing/provenance (Hyperliquid public data, derived, attributed), coverage cap (100 coins, OI-ranked), and the paid-access model including the exact failure path (unpaid calls return the x402 challenge; pay and retry). What is left out is error behavior beyond payment and any latency/rate limits, which keeps it off 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?

The payload and sign convention are front-loaded, then usage, freshness, and cost, which is a sensible order. It loses a point for redundancy: the $0.001 per-call price is stated in prose and then repeated almost verbatim in the bracketed payment note.

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-optional-parameter read tool with no output schema, the description supplies everything an agent needs: what fields come back, how to read the sign, how results are ordered and capped, how fresh the data is, and how to satisfy the payment gate. No material gap remains.

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

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

Schema coverage is 100% and the single `limit` parameter is already documented with its default and cap, so the schema does the heavy lifting. The description adds only the framing that the cap refers to coins ranked by open interest, which is marginal meaning beyond the schema; 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 names a specific verb and resource ('Latest Hyperliquid perpetual-funding snapshot') and pins down the payload precisely: hourly funding rate per coin with sign convention (positive = longs pay shorts) plus derived APR, ranked by open interest. Nothing here overlaps with the Polymarket siblings, so an agent can distinguish it without opening the schema.

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?

'Use when an agent needs current perp funding rates for a carry or basis view' gives a concrete triggering scenario rather than a generic 'get funding' framing. It does not name exclusions or alternatives, but the sibling set is a different domain (Polymarket odds/disagreement), so the routing risk is low.

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?

With no annotations, the description carries the full burden and does well: it discloses data sources, that values are derived and attributed, that freshness is tied to the collector batch, and the x402 payment flow including what happens on unpaid calls. It omits edge-case behavior such as what is returned when no matched pairs exist.

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 is front-loaded in the first clause and the usage guidance follows immediately. The only waste is the payment cost stated twice ('$0.02 per call' appears in both the body and the bracketed payment note).

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 usefully summarizes the return payload as per-pair gaps plus a max disagreement, and it explains cost and freshness. It does not state that the call is unconditional and returns the full pair set with no way to scope to a single market, which an agent would want to know before paying.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate beyond confirming the call is parameterless. Baseline for a no-param tool 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 names a specific verb+resource: cross-venue disagreement between Polymarket and Kalshi implied probabilities for matched questions, returning per-pair gap and max disagreement. It is distinguishable from siblings like curade_polymarket_odds because it is explicitly comparative rather than a single-venue price read.

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 when-to-use conditions: getting a second opinion before acting on a Polymarket signal, or detecting cross-venue mispricings. It does not explicitly say when NOT to use it or name curade_polymarket_odds as the fallback for single-venue pricing, so the routing guidance is clear but not exhaustive.

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?

With no annotations, the description carries the burden well: it discloses freshness ('Refreshed every collector batch'), provenance ('derived, attributed'), and a paid access model via x402 with the exact price and the unpaid-call challenge/retry behavior. It stops short of describing row ordering guarantees or failure modes beyond payment.

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 resource and fields, then usage, then behavioral details. The only waste is the payment cost being stated twice ('$0.005 per call' in prose and again in the bracketed payment note), which is mild redundancy.

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

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

There is no output schema, and the description compensates by listing the returned columns, plus freshness, provenance, and payment requirements. An agent could invoke it correctly from this text; only ordering/pagination behavior is left implicit.

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 both parameters (q, limit) are already documented in the schema, so the description adds no syntax or format detail beyond it. The phrase 'scan for a specific question' loosely signals the filter, but it is baseline-level value given the schema does the work.

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 ('Normalized Polymarket odds snapshot') and enumerates the row fields (question, yes/no prices, implied probability, 24h volume, liquidity), so the agent knows exactly what comes back. It does not explicitly differentiate itself from the polymarket siblings (disagreement, package), which keeps it short of a 5.

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

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

Gives concrete use cases: check whether a market moved after news, rank the busiest markets, or scan for a specific question. However, it never says when to prefer a sibling like curade_polymarket_disagreement or curade_polymarket_package, and offers 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?

With no annotations, the description carries the full burden and does so well: it discloses the one-time purchase/retention model, the flat $2.00 cost, the x402 USDC-on-Base payment rail, and crucially the failure path — unpaid calls return an x402 challenge that must be paid and retried. It does not describe response shape or any size/latency limits, so a small gap remains.

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 and the use case are front-loaded in the first two sentences, which is good. However, the payment information is stated twice — once as '$2.00 flat' and again in the bracketed '[Payment: $2.00 one-time...]' note — which is avoidable duplication.

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-annotation, no-output-schema tool, the description covers what is bought, why, how it is paid for, and what happens if payment is missing — enough for an agent to call it correctly. Only the returned artifact's shape and any delivery timing are left implicit.

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% for the single 'market' parameter (slug or condition id), so the schema already does the documentation work. The description only reinforces the one-market scope ('for ONE market'), adding little semantic detail such as validation behavior or what happens with an ambiguous slug.

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: a one-time purchase of a full attested Polymarket data package for exactly ONE market, enumerating contents (all snapshot rows, provenance, signed license token). This clearly differentiates it from sibling tools like curade_polymarket_odds and curade_polymarket_disagreement, which are live/derived views rather than a complete record.

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

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

Explicitly gives the selection condition: 'Use when an agent needs the complete record for one market rather than a live snapshot, e.g. for backtesting or an audit trail.' That contrast implicitly routes away from the live-snapshot sibling, though it never names that sibling directly or states when not to buy.

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