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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description does not contradict them. It adds substantial behavioral detail: returns top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict, per-leg fill detail, thin_legs[], forced_directional_risk. It also warns that partial basket fills convert an arb into an unhedged directional position, disclosing a key failure mode 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 long but well-structured with clear SINGLE-MARKET and BASKET sections. Every sentence adds functional detail or usage guidance; there is no fluff. The all-caps keywords help parse the two modes and the critical usage instruction. It is dense yet organized, earning its length.

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 4 parameters, two modes, no output schema, and no nested objects, the description is extraordinarily complete. It enumerates return values for both modes, explains parameter interpretation, identifies risk conditions (thin_legs, forced_directional_risk), and places the tool in its workflow context. No additional information is needed for correct invocation.

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%, but the description adds significant relational meaning: distinguishes single-market vs basket mode, explains how size_usd differs (max spend on buys vs target proceeds vs settlement notional), and clarifies default side behavior ('sell if partition sum > 1, buy if < 1'). This goes far beyond the individual parameter schemas.

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 it performs a 'Realizable-vs-theoretical edge check against live CLOB order-book depth' with specific mention of modes (single-market and basket). It explicitly differentiates from sibling tools by explaining that it should be used before acting on polymarket_arbitrage signals or large polymarket_edges trades. The verb 'check' and resource scope are unambiguous.

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?

Explicitly instructs when to use: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'. It also explains why (theoretical overround on thin books is not capturable, partial fills cause unhedged directional risk). This is clear when-to-use guidance with a direct alternative context.

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