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

Annotations indicate readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds rich behavioral context beyond these: it reveals that the tool 'walks the ladder' and returns verdicts (clean|degraded|cannot_fill), explains that partial basket fills convert arb into unhedged directional positions, and mentions forced_directional_risk. There is 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 fairly long but well-structured with clear mode separators (SINGLE-MARKET, BASKET) and bullet-like formatting. It is front-loaded with the core purpose and each section adds unique information. While dense, it avoids redundancy and earns its length. It could be slightly more concise, but it remains readable.

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 lacking an output schema, the description exhaustively lists the return fields for both modes (top_of_book, vwap_fill_price, slippage_pp, verdict, etc. for single-market; theoretical_sum, capture_ratio, thin_legs, etc. for basket). It also includes warnings about risk and edge cases. Given the complexity of dual modes and the absence of an output schema, this is a fully complete description.

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%, so baseline is 3. The description adds significant extra context: it clarifies that `size_usd` has different interpretations for single-market (max spend vs target proceeds) versus basket (settlement notional), and explains the default `side` logic for basket mode. This goes beyond the schema descriptions and meaningfully aids correct usage.

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 begins with a clear verb+resource pairing: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It then distinguishes between single-market and basket modes, and explicitly references sibling tools (polymarket_arbitrage, polymarket_edges) to clarify its unique role. This meets the highest standard of differentiation.

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 explicitly states 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.' It also specifies that one of `market` or `event` is required, and explains the consequences of not using it (partial fills leading to directional risk). However, it does not explicitly state when not to use the tool, which prevents a perfect score.

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