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

Annotations already indicate read-only, open-world, idempotent, non-destructive behavior. The description adds substantial context beyond that: how orders are simulated (walks the ladder), what metrics are returned (slippage_pp, shares_filled, max_fillable_usd), and the critical risk warning about partial basket fills converting an arb into an unhedged directional position. This gives the agent a clear model of the tool's internal behavior and edge cases.

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 carries information and the structure is clear with explicit sections for SINGLE-MARKET and BASKET, plus a usage warning at the end. It is slightly dense and could theoretically be trimmed, but given the tool's two-mode complexity, the length is justified. It front-loads the core purpose and then organized details.

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 fully covers return values for both modes, enumerating specific fields (top_of_book, vwap_fill_price, slippage_pp, verdict, etc.) and explaining the meaning of basket outputs like capture_ratio, thin_legs, and forced_directional_risk. It also explains the semantics of size_usd in each mode, making the tool fully usable without additional discovery.

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 100% with descriptions for all four parameters, but the tool description adds richer meaning: it explains how `side` defaults differently in single vs basket mode, how `size_usd` is interpreted as max spend vs target proceeds vs settlement notional depending on mode, and the exact distinction between `market` and `event`. This significantly enhances the agent's ability to choose and fill parameters correctly.

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 clearly states a specific verb and resource: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It distinguishes this tool from sibling tools by explicitly referencing them and framing this as the pre-trade verification step, making the unique purpose 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 guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains why it should be used (theoretical overround not capturable on thin books, partial fills create unhedged risk), effectively covering both when to use and the dangers of not using it. Alternatives are implicitly the signal-generation tools it complements.

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