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

The description goes beyond the annotations (readOnlyHint=true, etc.) by detailing what the tool returns, including verdicts (clean|degraded|cannot_fill), slippage, and risk indicators like forced_directional_risk. It also explains the practical implication of partial fills in basket mode, adding valuable behavioral context. There is no contradiction with the annotations, which declare the tool read-only, and the description consistently frames it as a check rather than an execution.

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 and dense, but it is well-structured with clear segments (SINGLE-MARKET, BASKET, USE THIS). The first sentence front-loads the core purpose. While every sentence carries useful information, some redundancy with the schema (e.g., defaults and clamps) slightly reduces conciseness. Overall, it is appropriately sized for a complex two-mode tool.

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?

The description is comprehensive: it covers both modes, all parameter semantics, return values in detail (top_of_book, vwap_fill_price, slippage_pp, etc.), usage guidance, and risk implications. Since there is no output schema, the description fully fulfills the burden of explaining what the agent will receive. It also explicitly ties to sibling tools and sets thresholds, making it complete in context.

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?

The input schema already covers 100% of parameters with descriptions, so the baseline is 3. The description adds strategic meaning beyond schema, such as interpreting side auto behavior in basket mode (sell if partition sum > 1, buy if < 1) and explaining size_usd as settlement notional in basket mode (shares per leg, each paying $1). This enriches the agent's understanding of how to set parameters for intent.

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 clear statement: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It then details two distinct modes (single-market and basket) with specific inputs and outputs, making it clearly distinct from sibling tools like polymarket_arbitrage and polymarket_edges. The verb 'check' and resource 'edge' against order-book depth precisely define the tool's function.

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?

Explicit guidance is provided: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains when not to rely on theoretical overround and warns about partial basket fills leading to unhedged directional positions. This directly addresses alternatives and timing, which is exemplary.

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