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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds rich behavioral context: walking the ladder, returning a verdict (clean|degraded|cannot_fill), and warning that partial basket fills convert an arb into an unhedged directional position. This significantly enhances understanding of tool behavior beyond 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 with clear sections for single-market and basket modes, a usage admonition, and detailed return fields. Every sentence provides value, though some redundancy (e.g., repeating mode explanations) could be slightly trimmed without loss. It earns its length given the complexity.

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?

Without an output schema, the description fully enumerates return values for both modes: top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict for single-market; theoretical_sum, realizable_sum, capture_ratio, profit_usd, per-leg fill detail, thin_legs, max_clean_notional, forced_directional_risk for baskets. It also covers edge cases (partial fills, thin legs) and dominant loss mode. Complete for a tool of this complexity.

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%, so baseline is 3. The description goes further by explaining the interplay between parameters: how `market` and `event` select modes, how `side` defaults for baskets, and how `size_usd` is interpreted differently for buys/sells and basket settlement notional. This adds meaning beyond the schema's terse 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 clearly states the tool's purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It distinguishes single-market and basket modes, and explicitly ties usage to related tools like polymarket_arbitrage and polymarket_edges, making it highly specific and differentiated.

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 provides explicit guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains why (theoretical overround not capturable on thin books, partial fills cause directional risk) and when not to use it (implied for small trades or when not arbitrating).

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