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

While annotations already indicate a safe read-only operation (readOnlyHint=true, destructiveHint=false), the description goes well beyond them by detailing behavior: it walks the order-book ladder, returns specific fields (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd), and exposes basket-mode internals (per-leg fill detail, thin_legs, forced_directional_risk). It also surfaces a critical behavioral risk: partial basket fills convert an arb into an unhedged directional position. No contradiction with annotations exists.

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 fairly long but front-loaded with the core purpose. It is well-structured with clear labels for SINGLE-MARKET and BASKET modes, and each sentence carries substantive information. While it could be trimmed slightly, the length is proportionate to the tool's complexity (two modes, multiple parameters, risk behavior). It earns a 4 rather than a 5 because some redundancy exists (e.g., size_usd semantics are repeated in schema and description), but it remains highly readable.

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?

This tool has no output schema, so the description must explain return values—and it does comprehensively for both modes. It covers parameter interpretation, mode selection, return fields, edge cases (thin_legs, forced_directional_risk), and the operational context (when to use before arbitrage/edge trades). Given the tool's complexity (4 optional params, two modes, no output schema), the description is exceptionally complete without requiring the user to guess 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 description coverage is 100%, so the baseline is 3. The description adds value by clarifying that one of market or event is required, which the schema (all optional parameters) does not convey. It also reinforces the meaning of size_usd in both modes ('max spend on buys, target proceeds on sells' and 'settlement notional S (shares per leg; each share pays $1)') and explains the default side behavior for baskets. This adds semantic nuance beyond the schema, justifying a 4 rather than a 3.

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 and resource: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes the tool's role from siblings like polymarket_arbitrage and polymarket_edges by stating 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' The two modes (single-market and basket) are explicitly named and detailed, 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 gives explicit when-to-use guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500—theoretical overround on thin books is not capturable, and partial basket fills convert an arb into an unhedged directional position.' It also clarifies mode selection by explaining that market is for single-market mode and event is for basket mode, and describes the distinction between single-market and basket parameter semantics. This is clear, actionable usage guidance.

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