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

Annotations already mark the tool read-only/idempotent, and the description adds valuable behavioral detail: it walks the order-book ladder, returns verdicts (clean|degraded|cannot_fill), exposes thin_legs and forced_directional_risk, and warns about partial-fill exposure turning arb into directional position. 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 structured into clear mode blocks (SINGLE-MARKET/BASKET) with a front-loaded summary and a crisp 'USE THIS' callout. It is long, but every block adds necessary detail for a dual-mode tool; could be slightly tighter around repeated size semantics.

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 key return fields for both modes (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict; theoretical_sum, realizable_sum, capture_ratio, profit_usd, per-leg fill detail, thin_legs, max_clean_notional_usd, forced_directional_risk). It also covers both parameter modes and gives rationale, making it effectively self-contained for the agent to invoke correctly.

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?

Input schema has 100% parameter coverage with detailed descriptions for side, event, market, and size_usd. The tool description reinforces and clarifies the semantics, especially the mode requirement (requires one of market or event) and size_usd interpretations for buys vs sells and basket settlement notional, adding modest value beyond the schema.

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?

Description opens with 'Realizable-vs-theoretical edge check against live CLOB order-book depth,' a specific verb+resource framing that clearly separates it from pure arbitrage detection siblings. It distinguishes single-market and basket modes explicitly, and references sibling tools (polymarket_arbitrage, polymarket_edges) in the usage guidance, making its unique role 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?

Explicit 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500' provides a clear trigger condition. It also explains why (theoretical overround on thin books not capturable) and identifies the risk of partial fills, giving the agent decision rules.

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