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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds rich behavioral detail beyond those: it walks the order book ladder, returns verdicts (clean|degraded|cannot_fill), names 'thin_legs' and 'forced_directional_risk' in basket mode, and explains how size_usd is interpreted differently in each mode. This is substantial contextual disclosure.

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 information-dense, with mode-specific details, return fields, and risk rationale all earning their place. It is front-loaded with purpose and requirements before elaborating on each mode. It could be slightly tightened, but every sentence adds meaningful guidance.

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?

This is a complex tool with no output schema, yet the description thoroughly enumerates what the caller receives: 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, and forced_directional_risk. It also explains failure modes and the danger of partial fills, making it complete for an AI 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?

The schema already covers 100% of parameters with descriptions, so baseline is 3. The description adds meaning by clarifying conditional requirements (market or event), mode-dependent side defaults (auto in basket), and the dual interpretation of size_usd (max spend on buys vs target proceeds on sells, settlement notional in basket). This exceeds the baseline.

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 purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes the tool from sibling tools by naming polymarket_arbitrage and polymarket_edges as consumers of the output, and it separates single-market vs basket modes with concrete semantics.

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?

Usage is explicit: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains when each mode applies (single-market vs basket), how defaults are chosen, and why using it is important (theoretical overround not capturable on thin books, partial fills convert arb to directional risk).

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