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

Annotations state readOnly and non-destructive, but the description adds critical behavioral context: it reveals the risk of partial basket fills converting arb into unhedged directional positions, names the 'forced_directional_risk' output, and clarifies that size_usd semantics differ between buy/sell and modes. This goes well beyond the structured 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?

Although long, the description is densely packed and structurally sound: it uses MODE headers, lists return fields, and separates guidance from parameter semantics. Every sentence serves a purpose—detailing modes, parameters, outputs, and usage warnings—making it an efficient reference for a complex 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?

For a tool with no output schema and two complex modes, the description fully compensates by enumerating all return fields (top_of_book, vwap_fill_price, per-leg fill detail, thin_legs, etc.), explaining edge cases, and providing risk warnings. It is complete enough for an agent to select and invoke the tool correctly without external documentation.

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?

While schema coverage is 100%, the description significantly enriches parameter understanding: it explains that market vs event selects distinct modes, side defaults vary (buy_yes default in single, auto in basket), and size_usd means max spend on buys vs target proceeds on sells, or settlement notional in basket. This adds meaning beyond the schema's simple 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+resource phrase ('Realizable-vs-theoretical edge check against live CLOB order-book depth') and clearly defines two operational modes (single-market and basket). It distinguishes itself from siblings by explicitly referencing polymarket_arbitrage and polymarket_edges, making its unique function evident.

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 why (theoretical overround not capturable, partial fills create directional risk) and implies when not to use (small trades, no arb signal). This is exemplary guidance with clear alternatives.

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