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

The annotations are all benign (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false), and the description goes far beyond them by detailing the tool's behavior: walks the order-book ladder, computes VWAP and slippage, returns a verdict, and warns about thin books and forced directional risk. No contradiction 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 well-structured with clear labels (SINGLE-MARKET, BASKET) and uses all-caps for key guidance. It is relatively long, but every sentence provides valuable information. A minor improvement would be trimming redundant phrases, but overall it is efficient for the complexity of the 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 that there is no output schema, the description fully compensates by listing all return fields for both modes, including warnings about thin legs, forced directional risk, and the verdict categories. The description also covers the selection logic between modes and important edge cases (clamp on size_usd, default behavior). It is complete for the tool's domain.

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%, so the baseline is 3. However, the description adds significant context beyond the schema: it explains how size_usd is interpreted differently for single-market (max spend or target proceeds) vs basket (settlement notional, shares per leg), and how the side parameter defaults to 'auto' in basket mode based on partition sum. This additional semantic detail justifies a 4.

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 clear, specific verb-resource pair: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It explicitly distinguishes two modes (single-market and basket) and lists the return fields for each, making the purpose unmistakable. The sibling tools list includes polymarket_arbitrage and polymarket_edges, and the description directly states it should be used before acting on those signals, differentiating it effectively.

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 when-to-use guidance: '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 use it implicitly by specifying the trade size threshold and outlines the risk of partial basket fills converting an arb into an unhedged directional position. The required parameter modes are clearly stated.

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