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

Annotations already establish readOnly, idempotent, non-destructive behavior. The description adds crucial information beyond those annotations: the paid nature ($0.005/call), the required two-step x402 payment exchange, and the charging only when a result returns. This goes well beyond what structured annotations provide and directly affects agent decision-making.

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

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

The description is dense and every sentence earns its place, including the payment flow which is essential operational detail. It is not laid out in the cleanest structured form, and 'You are only charged when a result actually comes back' is a useful but slight restatement of the paid nature. Still, there is no fluff.

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

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

For a paid, two-step x402 tool with no output schema, the description is remarkably complete: it explains scope, fields returned, how to pay, the exact call sequence, and billing semantics. An agent has everything needed to invoke this tool correctly without guessing. The only omitted details are response formatting and default limit behavior, which are minor here.

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 only 50%: x402_payment has a schema description, while limit does not. The description compensates substantially for x402_payment by explaining the two-call flow and what payload to supply. Limit is not addressed in the description, but its name plus the min/max constraints make its role self-evident. The added payment workflow context lifts this above a baseline score.

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

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

The description clearly names the resource: Polymarket prediction markets tracked by HostDeFi (top ~100 by 24h volume), and lists the returned data points: market ids, questions, latest yes/no odds, and sampling stats. It lacks an explicit verb like 'get' or 'list', but the intended action is unmistakable. It also differentiates from siblings by emphasizing the live odds board and HostDeFi's own recorded series.

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

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

The description gives explicit invocation steps: call once without x402_payment to receive the accepts array, then call again with x402_payment set to the base64 X-PAYMENT payload. This is strong operational guidance. It does not explicitly contrast this with alternatives like predict_history, but the scope and payment flow make when to use it clear enough.

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