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

Annotations (readOnly, idempotent, non-destructive) are supplemented with rich behavioral detail: the tool 'walks the ladder', returns a verdict, identifies thin legs, and computes 'forced_directional_risk'. It warns about the dominant loss mode in arb bots. This goes far beyond the annotations, revealing internal behavior and risk scenarios without contradicting 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 and dense, but structured with clear mode labels (SINGLE-MARKET, BASKET) and a final 'USE THIS' directive. Every sentence adds functional information. Minor deduction for being a wall of text; it could be split into bullets for quicker parsing, but it remains appropriately sized for the tool's complexity.

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?

Given the absence of an output schema, the description comprehensively lists return values for both modes (e.g., vwap_fill_price, capture_ratio, thin_legs[], max_clean_notional_usd). It also covers prerequisites, parameter interpretation, and failure modes. The tool has two distinct modes and all relevant context is provided without missing critical aspects.

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 covers all parameters at 100%, but the description adds substantial meaning: it explains how `size_usd` is interpreted differently for buys (max spend) vs sells (target proceeds) vs basket (settlement notional S per leg), clarifies the side defaults (e.g., 'default auto from partition sum'), and distinguishes market vs event usage. This deepens schema semantics.

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 definition: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It explicitly names the resource (order-book depth) and the verb (check), and distinguishes two modes (single-market and basket). It also differentiates from siblings by referencing polymarket_arbitrage and polymarket_edges, making the tool's unique role obvious.

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?

Provides 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.' It also explains why (theoretical overround on thin books is not capturable, partial fills create unhedged positions) and how to select modes via required parameters. The direction is unambiguous and actionable.

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