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

Annotations already mark this as read-only/idempotent, but the description goes far beyond: it details exactly what is computed (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd), what the verdict means, and the specific return fields for basket mode. It discloses the risk of partial fills converting an arb into an unhedged position—a key behavioral trait not captured in annotations. No contradictions 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 long but packed with essential information for a complex tool. It is front-loaded with the core purpose and then organizes details by mode. Every sentence adds value; however, it could be slightly more scannable with bullet points for the two modes. Still, it earns a high score for density and clarity.

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 the tool has 4 parameters, dual modes, no output schema, and important risk implications, the description is remarkably complete. It enumerates the return fields, explains the verdict categories, and warns about partial-fill dangers. It also provides usage thresholds and links to related tools. There is no significant missing context.

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%, but the description adds significant contextual meaning beyond the schema. It clarifies the dual-mode interpretation of size_usd (max spend on buys, target proceeds on sells, vs settlement notional for basket), explains default side selection behavior, and defines what 'market' vs 'event' means. This goes well above the structured 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 states a precise purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes between single-market and basket modes, and explicitly contrasts with sibling tools like polymarket_arbitrage and polymarket_edges by stating it should be used before them. The verb 'check' plus resources (market/event, order-book depth) make the function unmistakable.

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?

This is exemplary. The description explicitly says 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also provides the reasoning: theoretical overround on thin books is not capturable, and partial basket fills cause unhedged directional risk. This gives clear when-to-use and which alternatives to prefer.

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