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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description fully aligns with these. It goes far beyond annotations by disclosing how the tool walks the order book, what fields it returns (e.g., slippage_pp, shares_filled, capture_ratio), and the specific risk of partial basket fills converting an arb into an unhedged directional position. This is rich behavioral context that directly informs the agent of consequences.

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 sentence earns its place. It is structured by mode (single-market/basket), enumerates exact return fields, and ends with a usage directive. Despite its length, it is front-loaded with the core purpose and never meanders. The density is justified by the complexity of the tool.

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, the description carries the full burden of explaining return values and system behavior. It does so exhaustively: for single-market it lists top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, and verdict; for basket it lists theoretical_sum vs realizable_sum, capture_ratio, profit_usd, per-leg fill detail, thin_legs[], max_clean_notional_usd, and forced_directional_risk. It also covers mode selection, defaults, and clamping, making the description self-sufficient for correct invocation.

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?

Although the schema has 100% description coverage, the tool description adds substantial meaning. It explains the two parameter modes ('SINGLE-MARKET' vs 'BASKET'), the interpretation of size_usd in each mode ('max spend on buys, target proceeds on sells' vs 'settlement notional S'), and the auto-detection of side in basket mode. This is exactly the kind of semantic enrichment that helps an agent choose correct values.

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, precise statement: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes itself from siblings by naming polymarket_arbitrage and polymarket_edges and positioning itself as the pre-trade risk check. The single-market vs basket modes are explicitly described, making the tool's function unmistakable.

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 when-to-use instructions: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It further explains why—theoretical edge on thin books is not capturable and partial basket fills create unhedged directional risk—thus providing both the trigger and the rationale.

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