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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds rich behavioral context: it 'walks the ladder' and returns top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict, capture_ratio, profit_usd, thin_legs[], forced_directional_risk, etc. It explains the mechanism of capturing overround/underround and the risk of partial basket fills, which goes well beyond the structured 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 long but well-organized into SINGLE-MARKET and BASKET sections, using colons to separate mode from details. It is front-loaded with the core purpose and includes no redundant filler. The final use-case sentence lands the 'when to use' guidance effectively.

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?

Given the tool's complexity (two modes, no required schema fields, no output schema), the description enumerates the return fields for both modes, names verdicts, and highlights failure modes like thin_legs and forced directional risk. It provides enough information to invoke the tool correctly without needing to guess at outputs or behavior.

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 descriptions cover 100% of parameters, but the description adds essential meaning beyond them: it states 'REQUIRES one of `market` or `event`', explains that `size_usd` is interpreted as settlement notional in basket mode ('shares per leg; each share pays $1'), and clarifies default side behavior for each mode. This significantly reduces ambiguity.

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 verb-resource pairing: '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 positioning itself as a pre-trade risk assessment: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.'

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?

Provides explicit when-to-use guidance: before arbitrage signals or edge trades above ~$500, and warns why partial fills are dangerous. It also outlines two usage modes (single-market vs basket/partition) and explains how to select the appropriate `market` or `event` parameter, and what each side means in each mode.

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