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

The description thoroughly discloses behavior beyond the readOnlyHint and idempotentHint annotations. It details the returned fields (top_of_book, vwap_fill_price, slippage_pp, verdict, etc.), explains the interpretation of size_usd in each mode, and calls out edge cases like thin_legs and forced_directional_risk. It also warns about the risk of partial basket fills, which is critical behavioral context for a risk-check tool. No contradiction with annotations exists.

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?

Despite its length, the description is tightly packed with value and extremely well-structured. It front-loads the core purpose, uses ALL-CAPS markers to delineate REQUIRES, SINGLE-MARKET, BASKET, and USE THIS sections, and every sentence adds unique information (modes, defaults, return fields, risk warning). No filler or redundancy exists, and the length is proportionate to the tool's 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?

With no output schema, the description compensates by enumerating all major return values (top_of_book, vwap_fill_price, verdict, theoretical_sum, capture_ratio, thin_legs, etc.) and explaining their meaning. It also covers both modes, parameter defaults, and the key risk scenario (partial basket fills). The complexity of a two-mode risk-check tool is fully addressed, leaving no critical gaps.

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?

The input schema already provides rich descriptions for all parameters (100% coverage), establishing a baseline of 3. The tool description adds extra semantic value by clarifying the mutual exclusivity of market vs event ('REQUIRES one of market or event'), explaining how size_usd affects ladder walking for single-market mode, and defining the auto side behavior in basket mode. This goes slightly beyond what the schema states, so a 4 is warranted rather than a 5 (which would require even more novel parameter context).

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 clear verb+resource: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It immediately distinguishes this tool from siblings by naming polymarket_arbitrage and polymarket_edges, and explains that it checks fill feasibility rather than detecting edges. The two modes (single-market and basket) are explicitly defined with distinct purposes.

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?

Explicit usage guidance is provided: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains when NOT to rely on theoretical overround, warning that partial basket fills convert an arb into an unhedged directional position. This clearly differentiates it from sibling tools and gives a concrete decision threshold.

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