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

Annotations already declare read-only, idempotent, and non-destructive hints. The description adds substantial behavioral context: it walks the order-book ladder, returns specific fill metrics, and warns about the risk of partial basket fills converting an arb into a directional position. It also discloses default clamping and mode-specific semantics, exceeding what annotations provide.

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 lengthy but carefully structured: purpose statement, mode requirements, explicit usage directive. Every sentence contributes necessary detail for the tool's complexity, and the format (SINGLE-MARKET / BASKET / USE THIS) aids scannability. It could be trimmed slightly, but the length is justified by the tool's dual-mode 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?

With no output schema, the description enumerates all return fields for both modes (top_of_book, vwap_fill_price, slippage_pp, verdict, capture_ratio, thin_legs[], etc.) and explains the risk interpretation of partial fills. It covers input requirements, defaults, and usage context, making it self-sufficient for an agent to decide when and how to invoke the tool.

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?

The input schema already covers all 4 parameters with 100% coverage, including defaults and mode-specific descriptions. The tool description enriches this by explaining how size_usd means different things in each mode (max spend on buys vs target proceeds on sells vs settlement notional in basket mode) and clarifies the intent of each side value. This adds value beyond the schema, though the schema already does a good job.

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 definition: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly differentiates single-market and basket modes, and references sibling tools (polymarket_arbitrage, polymarket_edges) to position its role. This goes beyond a vague verb+resource and distinguishes the tool from alternatives.

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?

Explicitly states '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 vs basket modes and why the check is necessary (theoretical overround not capturable, partial fills create unhedged positions). This provides clear, actionable guidance with alternatives named.

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