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

No annotations are provided, so the description carries the full burden and does well: it discloses the 15-minute staleness, that access is free via x402, that the output is derived analytics, and that the calibration claim is externally audited. It stops short of describing pagination or row-count behavior.

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 disagreement-ranking concept and pushes the delayed-vs-realtime caveat and HTTP details to the end. The opening clause ('ran…') appears truncated, and the middle sentence is dense, but the structure is otherwise economical and well ordered.

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 supplies the return contents (direction, each venue's liquidity, calibration verdict), the latency, and the access cost — enough for an agent to call it correctly. Missing only minor operational detail like row limits or ordering ties.

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% for both params (min_gap, category), so the schema already documents filtering. The description adds no syntax or semantics beyond what the schema states, making the baseline 3 appropriate.

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: active prediction markets priced on both Kalshi and Polymarket, ranked by cross-venue implied-probability disagreement. It also names the sibling it differs from (the realtime /v1/cross-venue/disagreement endpoint), so an agent can separate the delayed variant from the paid one without opening a 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?

Explicitly routes the agent: 'Use the paid endpoint for realtime data,' and frames this as the delayed variant served at least 15 minutes stale. That gives a clear condition selecting between the two variants, though it doesn't discuss when this tool beats other probability siblings beyond the delayed/realtime axis.

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