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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds significant 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), explains the basket-mode interpretation of size_usd, and warns about forced_directional_risk. It does not describe rate limits or auth, but given the annotations, the extra detail justifies a 4 rather than a 3.

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-packed, but it is structured with clear sections (SINGLE-MARKET vs BASKET) and uses abbreviations and lists to compress a lot of detail. It is longer than ideal but every sentence adds value, covering modes, parameters, return fields, and usage guidance. The front-loading of the core purpose and the warning at the end make it effective despite length.

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?

The tool has 4 parameters, no required params, 100% schema coverage, no output schema, and no nested objects. Given no output schema, the description compensates by enumerating key return fields for both modes (top_of_book, vwap_fill_price, etc.). It also covers the two main modes, defaults, and risk warnings. It lacks some details like pagination or error cases, but for a read-only analysis tool with rich annotations, it is largely 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?

Schema description coverage is 100%, so the schema already defines each parameter. The description goes beyond by explaining the distinction between single-market and basket modes for each parameter, clarifying the default behaviors (e.g., side default 'buy_yes' for single-market, 'auto' for basket), and interpreting size_usd differently per mode ('max spend on buys, target proceeds on sells' vs 'settlement notional S'). This adds meaning beyond the schema's basic type/description, meriting a 4.

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 has a specific verb ('check') and resource ('realizable-vs-theoretical edge against live CLOB order-book depth'), and it clearly distinguishes the tool from siblings like polymarket_arbitrage and polymarket_edges by focusing on fill risk and market depth. It also specifies two distinct modes (single-market and basket) with concrete actions and outputs.

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 ('before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500') and explains why (theoretical overround is not capturable on thin books; partial fills convert arbs into unhedged directional positions). It also names sibling tools and specifies the context, making the usage guidance highly actionable.

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