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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint true and destructiveHint false. The description adds valuable behavioral context: it walks the order book ladder, returns fill details (top_of_book, vwap, slippage, etc.), and for basket mode warns about forced_directional_risk and thin legs. It also explains the risk of partial fills converting arbitrage into unhedged positions. This adds significant transparency beyond annotations, though it does not explicitly restate the read-only nature.

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 fairly long with multiple sentences and two large blocks (SINGLE-MARKET and BASKET). While well-structured with clear section headers, it repeats some information (e.g., modes are described twice). Some sentences are dense and could be split for readability. It is not maximally concise given the complexity, but it is organized logically.

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?

Despite no output schema, the description compensates by listing all return fields (top_of_book, vwap_fill_price, slippage_pp, etc.) with their meanings. It explains the tool's purpose, when to use it, and failure modes (partial fills, thin books). The 4 parameters are fully covered with defaults and constraints. Given the tool's complexity and risk warnings, the description is thorough.

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% for all 4 parameters. The description enhances this by explaining the 'auto' default for side in basket mode, specifying the clamp range for size_usd (10–1,000,000), and clarifying the interpretation of size_usd in single-market vs basket mode. For market and event, it explains the mode they enable. The description adds meaning beyond the schema's property 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 starts with a specific action ('realizable-vs-theoretical edge check against live CLOB order-book depth') and clearly defines two modes (single-market and basket). It differentiates from siblings like polymarket_arbitrage and polymarket_edges by explicitly stating when to use this tool ('USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'). The verb+resource+scope is highly specific and unique among siblings.

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 usage context: it requires either 'market' or 'event', explains the default side and size_usd, and clearly states when to use this tool (before acting on arbitrage signals or large trades). It also explains why it is necessary ('theoretical overround not capturable', 'partial fills convert arb into directional position'), giving both positive and negative usage guidance. The sibling differentiation is strong and actionable.

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