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

Annotations indicate read-only, idempotent, non-destructive. The description adds extensive behavioral context: it walks the order-book ladder, returns specific metrics (vwap_fill_price, slippage_pp, shares_filled), warns about partial fills and strand risk, and details basket-mode settlement notional. This goes far beyond the annotation hints and provides real operational transparency.

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 single dense paragraph is front-loaded with the core purpose, then clearly partitions SINGLE-MARKET and BASKET modes. Every sentence carries specific information: defaults, output fields, risk caveats, and use-case trigger. There is no padding; the length is justified by 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?

Given the tool has two modes, no output schema, and 4 parameters, the description enumerates all relevant return fields for both modes (top_of_book, vwap_fill_price, slippage_pp, capture_ratio, thin_legs[], forced_directional_risk, etc.), explains the risk model, and specifies the ~$500 threshold. This is a complete operational picture for an agent.

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%, but the description adds significant meaning: it explains the dual mode of `market` vs `event`, the default and permuted meanings of `side` per mode, and the nuanced interpretation of `size_usd` (max spend on buys, target proceeds on sells, settlement notional for baskets). This provides semantic richness beyond the schema's brief 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 opens with a specific verb+resource: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly differentiates between single-market and basket modes, and the title+use case distinguishes it from siblings like polymarket_arbitrage, polymarket_edges, and polymarket_kalshi_spread.

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 tool explicitly instructs when to use it: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains why (theoretical overround on thin books is not capturable, partial basket fills convert an arb into unhedged directional position). This is exemplary usage guidance with alternatives and rationale.

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