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

The description provides extensive behavioral context beyond the annotations: it details the ladder-walking computation, return fields (top_of_book, vwap_fill_price, slippage_pp, verdict, etc.), mode-specific interpretation of size_usd, and the failure mode of partial basket fills ('convert an arb into an unhedged directional position'). It also warns about thin books and lists forced_directional_risk as a return. Annotations only state readOnly/idempotent; the description adds far more.

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 highly structured with bolded mode indicators (SINGLE-MARKET, BASKET) and a direct 'USE THIS' instruction. Every sentence adds functional value, and content is front-loaded with purpose. It loses a point for sheer length, but the organization makes it scannable.

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?

In the absence of an output schema, the description fully enumerates all return values for both modes, explains the interpretation of results (e.g., theoretical_sum vs realizable_sum, capture_ratio, profit_usd), and contextualizes the tool's place in a workflow. It even names the specific sibling signals it should precede. Complete for the tool's 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 coverage is 100%, and the schema descriptions are already detailed. The description adds critical non-obvious semantics: the requirement of exactly one of `market` or `event`, the default of `side` in basket mode ('auto from partition sum'), and how `size_usd` is interpreted differently in each mode. This boosts the value above schema baseline, though the schema itself already covers some of the same semantics.

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 precise statement: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' This uses a specific verb ('check') and resource ('live CLOB order-book depth'), and clearly distinguishes the tool from siblings like polymarket_arbitrage and polymarket_edges by focusing on fill risk verification rather than trade discovery or execution.

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 guidance is embedded: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains when to use single-market mode vs basket mode, and clarifies the downside of not using it (partial fills → unhedged directional risk). This is model guidance for when to choose this tool and when not to.

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