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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds rich behavioral context: mode-specific behavior (single vs basket), parameter interpretation (size_usd as spend vs notional), return fields (top_of_book, vwap_fill_price, slippage_pp, etc.), and risk disclosure (partial basket fills convert an arb into an unhedged directional position). 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 front-loaded with the core purpose and then systematically covers mode details, return values, and usage warnings. It is dense and long, but every clause carries either mode-specific or risk-relevant information. The length is justified by the tool's complexity, yet it could be better organized (e.g., bullet lists) for readability.

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?

Given no output schema, the description provides a thorough enumeration of return fields for both modes (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict; for basket: theoretical_sum, realizable_sum, capture_ratio, profit_usd, per-leg fill detail, thin_legs[], max_clean_notional_usd, forced_directional_risk). It also covers parameter semantics, defaults, and use-case context, making it contextually complete for a complex dual-mode 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?

Although schema coverage is 100%, the description goes well beyond schema descriptions. It explains the dual meaning of size_usd ('max spend on buys, target proceeds on sells' vs 'settlement notional S'), default values, clamping (10–1,000,000), and side auto-selection logic in basket mode. This adds material semantic value for 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 opens with a specific verb+resource: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes this tool from siblings like polymarket_arbitrage and polymarket_edges by focusing on fill risk and order-book depth validation, not just edge discovery.

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 explains the rationale (theoretical overround on thin books is not capturable) and names the exact alternative tools, satisfying the when/when-not criteria.

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