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

Annotations already declare readOnlyHint=true, so the read-only nature is known. The description adds behavioral details beyond annotations: it walks the order-book ladder, returns specific fields (e.g., top_of_book, vwap_fill_price, slippage_pp), and warns about partial basket fills converting an arb into an unhedged directional position. This provides valuable transparency about the tool's effects and limitations.

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 relatively long but efficiently structured: it starts with the core purpose, then explains two modes with bullet-like detail, and ends with usage guidance. All sentences add necessary information; however, the dense text could be slightly more scannable with explicit bullet points for return fields. Still, it is concise for the complexity covered.

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 the tool's complexity (two modes, multiple return fields) and the absence of an output schema, the description provides detailed information about the output structure and behavioral nuances (e.g., thin_legs, forced_directional_risk). It explains the purpose of the risk check and the consequences of partial fills. This is sufficient for an AI agent to understand when and how to use the 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?

Schema description coverage is 100%, but the description adds significant operational semantics: it explains how 'size_usd' is interpreted differently in single-market vs basket mode, and clarifies the default behavior for 'side' in basket mode (auto from partition sum). This goes beyond the schema's parameter descriptions and helps the agent understand parameter interplay.

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 clearly states it performs a 'Realizable-vs-theoretical edge check against live CLOB order-book depth' and distinguishes itself from sibling tools (polymarket_arbitrage, polymarket_edges) by specifying when to use it: before acting on those signals or for trades above ~$500. It also outlines two modes (single-market and basket) with specific verbs and resources.

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 the tool ('USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500') and explains the two modes requiring either 'market' or 'event'. It provides clear context but does not explicitly state when not to use it, which would strengthen clarity further.

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