Infiniterb Bean Trader

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

With no annotations, the description carries the full burden and discloses key behavior: this is a paid tool ($0.002 USDC on Base via x402), requires a two-step handshake, and specifies the exact mechanism (_meta['x402/payment']). It also describes the return format. It omits details like pagination, rate limits, or error handling, but the payment and return behavior is unusually well documented for a tool without annotations.

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

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

The description is front-loaded with purpose and return information, then efficiently covers the essential payment flow. Every sentence earns its place, though the payment instructions are dense and could be slightly more scannable. It avoids redundancy and stays focused on what an agent needs to call the tool.

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 no annotations, no output schema, and a paid interaction model, the description is largely complete: it covers purpose, return contents, cost, network, and the payment handshake. It does not explain pagination, error behavior, or search nuances, but the critical behavioral and invocation details are present. Missing elements are minor for a two-parameter search tool.

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

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

Schema description coverage is 100%, so both parameters (q and limit) are fully documented in the schema, including defaults, min/max, and meaning. The description adds no parameter-specific syntax or format details beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description states a specific verb and resource: 'Search Polymarket prediction markets (V2)', and clarifies the return payload as 'events with market questions, volume and liquidity'. This distinguishes it from siblings like poly_odds, poly_signals, and poly_whales, which imply different resource types. An agent can immediately identify that this tool searches markets rather than retrieving odds or signals.

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

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

The description explains the paid invocation flow (first call returns payment terms, retry with payment), but it does not state when to use this tool versus alternatives such as poly_odds or poly_signals. No conditions, exclusions, or sibling comparisons are provided. Usage is implied only by the resource name, not by explicit guidance.

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

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

With no annotations, the description carries the full behavioral burden and does well: it discloses that calls are paid, the exact price ($0.005 USDC), the chain/network (Base, eip155:8453), the x402 payment mechanism, and the two-step handshake. It omits failure modes, rate limits, and caching/freshness guarantees.

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

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

Three sentences, front-loaded with the payload description before constraints and payment mechanics. Every clause earns its place: no padding, no restating the tool name.

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 and no annotations exist, so the description must cover everything, and it does cover the return contents and the payment flow. It is slightly short on error behavior and freshness/polling expectations for what is billed as a 'live' snapshot.

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 single market_id parameter is already documented as a condition_id in the schema. The description adds no format, example, or validation detail beyond that, so the baseline 3 for full schema coverage applies.

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

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

States a specific verb and resource ('Live odds snapshot for a Polymarket market') and enumerates the payload (outcome prices, order-book top bids/asks, spreads), so an agent knows exactly what data comes back. It does not explicitly differentiate itself from siblings poly_markets/poly_signals/poly_whales, leaving that routing to inference.

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 a clear scope constraint ('V2 markets only') and an explicit invocation protocol: call once unpaid to get terms, then retry with payment in _meta['x402/payment']. That is actionable usage guidance. It stops short of saying when to prefer this tool over the sibling odds/signal/market tools.

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

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

With no annotations, the description carries the full behavioral burden and does so: it discloses the price ($0.02 USDC on Base eip155:8453), the x402 payment mechanism, the refresh cadence (every 5 minutes), and the two-step paid-call handshake. Cost, cadence, and payment flow are exactly the traits an agent must know 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?

Three tightly packed sentences, front-loaded with what the tool produces, then cadence, then the payment workflow. No filler; each clause carries operational meaning.

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 and no annotations, the description compensates by naming the returned per-signal fields (direction, confidence, reasons) and fully explaining the payment lifecycle. An agent has everything needed to call it correctly.

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

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

The schema has zero parameters, so the baseline is 4; the description goes further by documenting the non-schema payment parameter (_meta['x402/payment']) that governs actual invocation. It clarifies an otherwise invisible input contract.

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 ('computed mispricing signals' for Polymarket) and enumerates the inputs (order-book imbalance, 24h momentum, whale flow) and outputs (direction, confidence, reasons). This distinguishes it from raw-data siblings like poly_markets/poly_odds because it is explicitly a derived signal product.

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

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

Gives an explicit invocation protocol: call once with no payment to receive terms, then retry with payment in _meta['x402/payment']. It does not, however, say when to prefer this tool over the sibling market/odds/whale tools, so the when-to-use guidance is incomplete.

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 behavioral burden and largely succeeds: it discloses that the tool is paid, the exact price ($0.01 USDC), the chain (Base, eip155:8453), per-call charging, and the two-step x402 negotiation flow. It stops short of covering rate limits or response shape beyond naming the fields.

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

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

Three sentences, front-loaded with what the feed is, followed by the payment mechanics and the required call sequence. No filler, though the payment block is dense with identifiers that could be separated for scannability.

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 small two-parameter paid feed with no output schema, the description supplies the essential missing context: cost, chain, and the mandatory unpaid-then-paid invocation sequence. It omits nothing critical, though return pagination/limits are 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%, so the schema already documents both market_id (condition_id) and min_usd (default 1000). The description restates 'above a USD threshold' without adding syntax, units, or range constraints beyond 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 description gives a specific verb and resource: a 'large-trade feed for a Polymarket market' returning whale buys/sells above a USD threshold with wallets and tx hashes. That is far more informative than the bare name, but it never contrasts itself with the sibling feeds (poly_signals, poly_odds), so an agent must infer the boundary.

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 states the invocation protocol for the paid endpoint (call once unpaid to get terms, then retry with payment in _meta['x402/payment']), which is real operational guidance. However, it gives no guidance on when to choose this feed over poly_signals or poly_odds; usage is only implied by the 'large-trade' framing.

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