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

Annotations already declare read-only and non-destructive, but the description adds substantial behavioral detail: it walks the order-book ladder, returns specific fields (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict), and explains basket-mode risks like forced_directional_risk and partial-fill conversion to unhedged positions. It also discloses interpretation of size_usd for both modes. 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 dense and information-rich, with a clear opening statement, distinct mode explanations, and a final usage directive. While it is a long single paragraph, every sentence contributes meaningful detail, and the complexity of the tool justifies the length. Minor deduction for lack of visual structure (e.g., bullet points or mode headers) that would aid scanning.

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?

There is no output schema, so the description carries full responsibility for explaining return values. It enumerates all key return fields for both modes, including edge-case alerts (thin_legs, forced_directional_risk, max_clean_notional_usd), and explains the verdict options. For a high-complexity tool with dual modes and no structured output metadata, the description is remarkably complete.

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 has 100% coverage with detailed per-parameter descriptions, so baseline is 3. The description adds cross-mode semantics that the schema fields alone do not fully convey, such as 'size_usd (default 1000 — max spend on buys, target proceeds on sells)' and the basket-mode interpretation as settlement notional. It also explains the auto-detection logic for basket side. This exceeds schema-only documentation.

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, action-oriented definition: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes from siblings by naming polymarket_arbitrage and polymarket_edges and explaining how fill risk is the prerequisite check for acting on those tools. The two modes (single-market and basket) are unambiguously described.

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 usage direction is given: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains when not to rely on theoretical values and warns about partial fills converting arbs into directional risk. This is exactly the kind of when-to-use vs. alternatives guidance needed.

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