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

Even with annotations declaring readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the description adds rich behavioral context: it 'walks the ladder,' returns detailed fields like top_of_book, vwap_fill_price, and a verdict (clean|degraded|cannot_fill), and warns about forced_directional_risk and thin_legs. It also discloses that partial basket fills convert arb into an unhedged directional position, which is critical behavioral information beyond the 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, front-loaded with the core purpose and structured via 'SINGLE-MARKET:' and 'BASKET:' labels. However, it is a long wall of text that repeats some schema details (e.g., default 1000, parameter modes) and enumerates many return fields that might be better in an output schema. It earns high marks for usefulness but loses a point for being somewhat verbose and borderline run-on.

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 complex tool with two modes, four parameters, no output schema, and a rich set of return values, the description is exceptionally complete. It covers all required inputs, explains default behaviors, lists comprehensive outputs including edge cases (thin_legs, max_clean_notional_usd, forced_directional_risk), and ties the tool into the broader arbitrage workflow. The annotations cover safety, and the description covers semantics, leaving no obvious 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 coverage is 100% with detailed descriptions for all four parameters, so the baseline is 3. The description adds meaningful nuance: 'side' in basket mode is explained as 'sell_yes = capture overround by selling every leg, buy_yes = capture underround,' and size_usd is clarified as 'max spend on buys, target proceeds on sells.' This goes beyond the schema's basic 'USD to spend' and aids parameter selection.

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 purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes itself from sibling tools like polymarket_arbitrage and polymarket_edges by framing this as the pre-trade risk validation step, and it details two distinct modes (single-market and basket) with unique 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 it: '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 is not capturable on thin books and partial fills create unhedged directional risk—providing clear context for when this tool is necessary versus alternatives.

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