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

Annotations declare readOnlyHint=true and idempotentHint=true, which the description aligns with (it's an analysis/check, not a mutation). The description adds substantial behavioral context beyond annotations: walks the ladder, returns verdict statuses, identifies thin legs, forced direction risk, and explains the dominant loss mode (partial basket fills converting an arb into unhedged 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 long, but every sentence carries operational information. It uses clear labels like 'SINGLE-MARKET' and 'BASKET' and ends with a usage directive. However, it is a dense wall of text without line breaks or bullet points, which slightly hurts scannability. It's appropriately sized for the tool's complexity, but could be structured better.

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 thoroughly enumerates all return values in 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 parameter defaults, clamping, mode selection, and usage context, making it fully complete for an 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?

Even though schema coverage is 100%, the description adds critical semantic meaning: clarifies that exactly one of `market` or `event` is required (REQUIRES one of), and explains how `size_usd` is interpreted differently in each mode ('max spend on buys, target proceeds on sells' for single-market vs 'settlement notional S (shares per leg)' for basket). This goes well beyond the schema's descriptions.

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 explains two modes (single-market and basket) and explicitly distinguishes itself from sibling tools like polymarket_arbitrage and polymarket_edges by placing itself as the pre-trade fill-risk check.

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 gives explicit, actionable guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains why (theoretical overround on thin books is not capturable, partial fills create unhedged directional risk), providing both when-to-use and strong implied when-not-to-use context.

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