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

Annotations only indicate read-only, open-world, idempotent, non-destructive. The description goes far beyond: it explains the walk-depth behavior, interpretation of size_usd for buys vs sells and for basket settlement notional, the verdict outcome (clean|degraded|cannot_fill), and the critical risk that 'partial basket fills convert an arb into an unhedged directional position' — a nontrivial behavioral caveat not derivable from the schema or 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 dense and slightly long, but every sentence earns its place by covering mode selection, parameter semantics, output fields, and a concrete usage warning. It is front-loaded with the core purpose, and the risk warning at the end is essential. A slightly more structured layout (e.g., labeling SINGLE-MARKET and BASKET) would improve scannability, but it remains economically worded.

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 two distinct modes and no output schema, yet the description enumerates all major return fields for both modes (e.g., theoretical_sum, realizable_sum, capture_ratio, thin_legs[], max_clean_notional_usd, forced_directional_risk). It also provides the necessary context of when to use it as a pre-trade check for other tools. The description is fully self-contained despite the tool's complexity.

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?

Even though schema coverage is 100%, the description enriches every parameter. It clarifies that `market` and `event` are mutually exclusive modes, explains that `side` has mode-specific allowed values and defaults (including auto-detection for baskets), and defines `size_usd` as spend for buys, target proceeds for sells, and settlement notional for baskets. It also mentions clamping ranges (10–1,000,000). This is far beyond the schema descriptions.

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+resource: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes between single-market and basket/partition modes, and names concrete return fields (top_of_book, vwap_fill_price, slippage_pp, etc.). This differentiates it from sibling tools like polymarket_arbitrage and polymarket_edges.

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?

Explicitly states 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also provides mode-selection rules: 'REQUIRES one of market (single-market mode) or event (basket/partition mode).' This both clarifies when to invoke and implies when to avoid (e.g., for small trades or when only theoretical edge matters).

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