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

Beyond the readOnlyHint, idempotentHint, and non-destructive annotations, the description reveals detailed behavior: it 'walks the ladder', returns specific fields like top_of_book, vwap_fill_price, slippage_pp, and identifies thin_legs and forced_directional_risk. It also warns about partial-fill dangers, which is critical behavioral context not captured by 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 densely packed with essential information: modes, parameters, outputs, and usage. It is front-loaded with the core purpose, then logically expands into requirements and details. While lengthy, every section serves a purpose, and the structure (SINGLE-MARKET vs BASKET) aids navigation.

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 no output schema, the description enumerates all return fields (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict; theoretical_sum, realizable_sum, capture_ratio, profit_usd, per-leg fill detail, thin_legs, max_clean_notional_usd, forced_directional_risk) and explains the risk context. It fully covers modes, parameters, and behavioral outcomes, making the tool well-specified.

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 schema already covers all parameters at 100% (baseline 3). The description adds contextual meaning by clarifying that exactly one of market or event is required, how size_usd is interpreted differently in single-market vs basket mode, and that values are clamped 10–1,000,000. This improves parameter understanding beyond the raw schema.

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 identifies the tool's function: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It specifies two distinct modes (single-market and basket) and differentiates from siblings like polymarket_arbitrage and polymarket_edges by focusing on fill risk rather than edge detection.

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 usage guidance is given: '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, and partial basket fills create unhedged directional risk. This provides clear when-to-use context and names the alternative tools.

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