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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds substantial behavioral detail beyond that: it discloses that the tool 'walks the ladder', returns specific verdicts (clean|degraded|cannot_fill), interprets size_usd differently for buys vs sells, and highlights risk leg behavior (thin_legs, forced_directional_risk). No contradiction with annotations is present.

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?

Though long, the description is tightly organized and front-loaded. It begins with the core purpose in one line, then uses clear section labels (REQUIRES, SINGLE-MARKET, BASKET, USE THIS) to structure the content. Every sentence adds functional value, from return fields to risk warnings. The density is justified by the tool's two-mode complexity.

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 present, the description compensates by enumerating all key return fields for both modes: top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict, theoretical_sum, realizable_sum, capture_ratio, profit_usd, per-leg fill detail, thin_legs, max_clean_notional_usd, and forced_directional_risk. It also covers prerequisites, defaults, and failure modes, making it highly actionable.

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?

While the schema covers all four parameters at 100% detail, the description adds critical semantics beyond the schema: the 'one of market or event' requirement, mode-specific side behavior (sell_yes = capture overround, buy_yes = capture underround, auto default), and the precise meaning of size_usd in basket mode (settlement notional, shares per leg). This is exactly the kind of interpretive guidance that helps an agent invoke correctly.

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 precise, specific statement: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly identifies the resource (Polymarket order books), the action (checking fill risk vs theoretical edge), and distinguishes two distinct modes (single-market and basket). It also differentiates from sibling tools by naming polymarket_arbitrage and polymarket_edges, making its purpose unmistakable.

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 also explains the consequence of not using it ('partial basket fills convert an arb into an unhedged directional position'), effectively providing a 'why' and 'when not to skip' guidance. It names the relevant sibling tools as alternatives/context.

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