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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds rich behavioral context: it walks the order book ladder, returns fields like top_of_book, vwap_fill_price, slippage_pp, etc. For basket mode, it explains per-leg fill details, thin_legs detection, and forced directional risk. It also explains the dominant loss mode. No contradictions with 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 long but well-structured: first sentence gives overall purpose, then REQUIRES line, followed by clear sections for SINGLE-MARKET and BASKET. The closing paragraph ties to usage guidelines. Every sentence is informative. However, it could be slightly more concise; some details about return fields could be abbreviated while still being clear. Still, very good 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?

Given there is no output schema, the description thoroughly explains return values for both modes, including verdict values (clean|degraded|cannot_fill), per-leg fill detail, thin_legs, forced_directional_risk, and max_clean_notional_usd. It covers edge cases like partial basket fills and thin books. For a 4-parameter tool with no output schema, this is exceptionally complete.

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 description coverage is 100%, but the description adds significant semantic value beyond the schema. It explains that `side` defaults based on partition sum in basket mode, `size_usd` has different interpretations for single-market vs basket (max spend vs target proceeds vs settlement notional), and specifies clamp range 10–1,000,000. This level of detail goes well beyond what the schema provides.

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 starts with a specific verb+resource: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes between single-market and basket modes, and the closing sentence explicitly differentiates it from siblings like `polymarket_arbitrage` and `polymarket_edges` by stating when to use this tool. This makes the purpose very clear.

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 explicitly says 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It warns about theoretical overround not being capturable on thin books and partial basket fills converting an arb into a directional position. While it does not explicitly list when not to use, the ~$500 threshold and the clear use case provide strong guidelines. A 5 would require explicit exclusions for all alternatives.

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