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

Annotations already mark the tool as read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds substantial behavioral context: it walks the order-book ladder, returns a verdict (clean|degraded|cannot_fill), flags thin_legs[], and warns that partial basket fills convert an arb into an unhedged directional position. It also explains the interpretation of size_usd in both modes, which goes far beyond the 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 well-organized with clear visual cues (REQUIRES, SINGLE-MARKET, BASKET, USE THIS) and front-loaded with its core purpose. It is long, but the tool is complex with two modes and many outputs; every section earns its place by explaining mode-specific behavior and return fields. A slight trim of the exhaustive output lists would improve conciseness without losing value.

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 and the absence of an output schema, the description compensates fully by enumerating the return fields (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict, theoretical_sum, realizable_sum, capture_ratio, profit_usd, per-leg fill detail, thin_legs[], max_clean_notional_usd, forced_directional_risk). It also covers prerequisites, mode selection, and risk explanation, making it complete for an agent to decide and even anticipate results.

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 input schema already has 100% parameter description coverage, so the description's additions are bonus value. It clarifies the mutual exclusivity of 'market' vs 'event' and adds the nuance that size_usd means 'max spend on buys, target proceeds on sells' in single-market mode and 'settlement notional' in basket mode. This is genuinely helpful beyond the schema, though the schema already covers most of the mechanics.

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 crisp, specific purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It explicitly names the resource (CLOB order book) and differentiates two modes (single-market vs basket), which clearly distinguishes it from related polymarket tools such as polymarket_arbitrage and polymarket_edges.

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 final paragraph gives explicit usage guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It names the alternative tools and provides a concrete threshold, plus a rationale (theoretical overround on thin books is not capturable, partial basket fills create unhedged directional risk). This leaves no ambiguity about when to choose this tool.

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