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

The description discloses extensive behavioral traits beyond the annotations: it walks the order book ladder, returns specific fields like top_of_book, vwap_fill_price, slippage_pp, shares_filled, and a verdict (clean|degraded|cannot_fill). It explains the risks of partial fills and forced directional risk in basket mode. The annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) are consistent with the description, and the description adds significant context about the tool's operational behavior and output semantics.

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 delivers essential information. It is front-loaded with a clear purpose, then uses structured markers (SINGLE-MARKET:, BASKET:) to walk through modes without wasted prose. The usage guidance is placed at the end as a practical 'when to use' rule. Given the complexity of the tool (two modes, multiple output fields, risk warnings), the length is justified and well-organized.

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 carries the full burden of explaining return values, and it does so comprehensively: it lists the return fields for both single-market and basket modes, explains the verdict values, and names the risk output (forced_directional_risk). It also provides essential operational context (size clamping, defaults, auto side selection). The description is complete enough for an agent to understand what the tool does, when to use it, and what results to expect.

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?

Although the input schema already provides 100% parameter coverage, the description adds critical semantic meaning. It explains the mutual exclusivity of `market` and `event` ('REQUIRES one of'), clarifies the interpretation of `size_usd` differently per mode ('max spend on buys, target proceeds on sells' vs 'settlement notional S'), and defines the `side` values' purpose in each mode ('sell_yes = capture overround', 'buy_yes = capture underround'). This goes well beyond the schema's basic field 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 clear, specific statement: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' This uses a precise verb ('check') and resource ('live CLOB order-book depth'), and it clearly distinguishes the tool from siblings by naming polymarket_arbitrage and polymarket_edges as related but different tools. The two modes (single-market and basket) are explicitly defined, leaving no ambiguity about what the tool does.

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 states exactly 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 also explains the reasoning ('theoretical overround on thin books is not capturable' and 'partial basket fills convert an arb into an unhedged directional position'), providing clear when/why guidance. It does not explicitly say when not to use, but the context implies alternatives (e.g., not using it for small trades or for other tools).

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