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

While annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, the description adds substantial context: it details how the tool walks the order-book ladder, returns specific fields like slippage_pp and forced_directional_risk, interprets size_usd differently per mode, clamps values, and warns about partial fills and unhedged positions. This goes far beyond the annotation-provided safety profile.

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 every sentence earns its place given the tool's complexity. It is well-structured: a one-line core purpose, a REQUIRES clause, distinct SINGLE-MARKET and BASKET sections, and a final usage directive. The front-loaded summary ensures the agent grasps the primary function immediately, while subsequent details justify the 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?

With no output schema, the description fully covers return values for both modes, listing outputs such as top_of_book, vwap_fill_price, capture_ratio, per-leg fill detail, and forced_directional_risk. It also addresses edge cases (thin_legs, partial fills) and provides usage context, making the tool complete for an agent to invoke correctly.

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%, but the description adds significant semantic value. It explains that `market` enables single-market mode and `event` enables basket mode, clarifies that `side` has mode-specific options (buy_yes/sell_yes in basket, auto default), and redefines `size_usd` as 'max spend on buys, target proceeds on sells' for single-market and 'settlement notional' for basket, including default and clamp behavior.

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 'Realizable-vs-theoretical edge check against live CLOB order-book depth,' a specific verb+resource statement that clearly defines the tool's function. It goes on to describe two distinct modes (single-market and basket) and lists concrete outputs, distinguishing it from siblings like polymarket_arbitrage and polymarket_edges by emphasizing fill risk and realizable versus theoretical edge.

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 final sentence explicitly instructs 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 why (theoretical overround on thin books is not capturable, partial basket fills convert arb into directional risk), providing clear context and exclusions implicitly.

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