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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond annotations: it walks the order-book ladder, returns slippage and fill-ability verdicts, and warns that partial basket fills convert an arb into an unhedged directional position. This goes beyond what annotations imply, though it does not mention rate limits or authorization.

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 deliberately structured with mode-specific sections (SINGLE-MARKET vs BASKET) and key terms in caps for scanning. Every sentence adds either mode behavior, return values, or risk context. The density is slightly high, but it avoids fluff and uses whitespace-like capitalization to maintain readability.

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 present, the description carries full burden for return-value disclosure, and it does so: it lists all key fields per mode (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict, etc.) and even includes the output for basket mode (theoretical_sum, realizable_sum, capture_ratio, profit_usd, thin_legs[], forced_directional_risk). It also explains the critical 'why' — why fill risk matters for arb strategies — making the tool self-contained.

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 high (100% of parameters described), but the description adds crucial per-mode semantics: size_usd is 'max spend' for buys vs 'target proceeds' for sells in single-market mode, but becomes 'settlement notional S (shares per leg)' in basket mode. It also explains the default side logic (auto based on partition sum) and the market/event requirement, which enriches the schema's basic property descriptions.

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 verb phrase 'Realizable-vs-theoretical edge check against live CLOB order-book depth,' clearly defining the tool as a fill-risk/slippage analyzer. It explicitly contrasts with sibling tools by naming polymarket_arbitrage and polymarket_edges in the usage guidance, distinguishing its role as a pre-trade validation step.

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?

Provides explicit when-to-use guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains the two modes (single-market vs basket) and when each is appropriate, plus the consequence of skipping this check (partial fills create unhedged directional positions).

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