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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavioral detail: ladder walking, return metrics (top_of_book, vwap_fill_price, slippage_pp, shares_filled, verdict), mode-specific semantics (basket sums vs single-market), and risk naming (forced_directional_risk, thin_legs). This exceeds what annotations convey and gives a rich picture of runtime behavior. No contradictions with 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 long but every major clause earns its place. It front-loads a one-sentence summary, then clearly sections SINGLE-MARKET vs BASKET, enumerates return fields, and ends with concrete usage guidance. The structure mirrors the tool's dual-mode nature, making dense information navigable. No filler or repetition exists.

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 tool's complexity (two modes, 4 parameters, no output schema), the description is fully self-sufficient. It explains inputs, outputs per mode, default values, clamps, risk indicators, and edge cases (partial fills, forced directional risk). It also places the tool in the broader workflow of arbitrage and edge trading. Nothing critical is missing.

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?

Though the schema covers 100% of parameters, the description adds critical interpretive meaning: size_usd is 'max spend on buys, target proceeds on sells' in single-market mode and 'settlement notional — shares per leg' in basket mode; side defaults are clarified and basket auto side explained. This is exactly the kind of parameter deep-dive that the schema alone doesn't provide.

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 opens with a specific, actionable definition: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes this tool from siblings like polymarket_arbitrage and polymarket_edges by focusing on fill risk and explicitly names those tools as and-candidates for pre-trade validation.

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 guidance is explicit and directive: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains the rationale (theoretical overround not capturable on thin books, partial fills create unhedged directional risk), giving clear when-to-use and why-to-use context that differentiates it from alternatives.

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