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

Annotations indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is safe and non-mutating. The description adds valuable behavioral details: it walks the order-book ladder, returns specific metrics like slippage_pp, verdict, capture_ratio, and forced_directional_risk, and warns that partial basket fills create unhedged directional risk. This goes well beyond the annotations without contradicting them.

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 well-structured with clear sections (SINGLE-MARKET, BASKET) and a bolded usage note. It is front-loaded with the core purpose, followed by detailed but necessary parameter and return information. Despite its length, every sentence adds value, and the formatting aids 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?

For a tool with no output schema, the description meticulously documents all return fields for both modes (e.g., top_of_book, vwap_fill_price, capture_ratio, thin_legs, forced_directional_risk). It explains the behavioral consequences of partial fills and the dominant loss mode. Given the complexity (two modes, multiple parameters), the description is comprehensive and leaves no critical gaps.

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% (each parameter has a description in the schema). However, the tool description adds significant meaning: it explains the difference between single-market and basket modes, the interpretation of size_usd as settlement notional for baskets, and the default behavior of the side parameter. This provides crucial context beyond the schema descriptions, justifying a score above the baseline of 3.

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 the tool performs a 'realizable-vs-theoretical edge check against live CLOB order-book depth,' specifying the verb (check) and resource (order-book depth). It distinguishes two modes (single-market and basket/partition), and its purpose is distinct from sibling tools like polymarket_arbitrage (which presumably creates trades) and polymarket_edges (which identifies edges).

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.' It explains the risks of not using it ('theoretical overround on thin books is not capturable, and partial basket fills convert an arb into an unhedged directional position'), providing clear context for when this tool is necessary.

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