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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, matching the description's read-only 'check' nature. The description adds substantial behavioral context beyond annotations: return fields (top_of_book, vwap_fill_price, slippage_pp, verdict), mode-specific behaviors (auto side selection), failure modes (thin_legs, forced_directional_risk), and the dominant loss mode (partial basket fills → unhedged directional position). No contradictions.

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 front-loaded with a one-sentence purpose, then clearly organized into SINGLE-MARKET and BASKET sections. Almost every clause adds new information (verdicts, per-leg fill detail, risk explanation). It is dense and uses uppercase labels for scannability, though the single giant paragraph could be more readable with line breaks; still appropriate for 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?

Despite having no output schema, the description enumerates all expected return values for both modes: top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict, theoretical_sum vs realizable_sum, capture_ratio, profit_usd, per-leg fill detail, thin_legs[], max_clean_notional_usd, and forced_directional_risk. It also covers edge cases like partial fills and auto side selection, making the tool fully predictable to 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%, so the baseline is 3. The description adds meaningful mode-specific semantics: for size_usd it clarifies 'max spend on buys, target proceeds on sells' in single-market and 'settlement notional S' in basket mode; for side it explains default auto in basket mode. This goes beyond the schema's generic parameter descriptions, justifying a 4.

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,' clearly distinguishing this from sibling tools like polymarket_arbitrage and polymarket_edges. It then enumerates both single-market and basket modes with specific inputs and outputs, leaving no ambiguity about what the tool does.

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?

Provides explicit usage guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500' and explains why (theoretical overround is not capturable, partial fills create unhedged risk). It also distinguishes when to use single-market vs basket mode, which is exactly the context an agent needs.

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