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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive, but the description adds substantial behavioral context. It reveals that the tool 'walks the ladder,' interprets size_usd differently per mode, returns per-leg fill details, and importantly discloses the risk of partial basket fills leaving an unhedged directional position. It even names the dominant loss mode and the forced_directional_risk output. No contradictions with 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 lengthy but extremely well-structured. It uses clear sections (SINGLE-MARKET, BASKET) and all-caps for critical requirements. Every sentence contributes unique information—no fluff. The length is appropriate given the tool's complexity and the absence of an output schema. It front-loads the purpose and then systematically details modes.

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 is complex (two modes, many outputs) and has no output schema, so the description carries the full burden of explaining return values. It does this comprehensively: it lists all key outputs for both modes (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). It also explains the interpretation of these outputs and the decision context. Nothing essential is missing.

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%, so baseline is 3. The description goes far beyond by providing mode-dependent meanings: size_usd as 'max spend' on buys, 'target proceeds' on sells, and 'settlement notional' in basket mode. It also explains the auto-detection of side in basket mode and the default values. This adds interpretive semantics that the schema alone does not convey.

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, specific purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It explicitly distinguishes two modes (single-market vs basket) and explains the core outputs. Crucially, it differentiates itself from siblings by naming the exact tools and signals it supports (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?

Guidelines are exceptionally clear. It states 'REQUIRES one of market or event' and provides explicit direction: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains when the tool is necessary (theoretical overround on thin books is not capturable) and the risk of partial fills. This covers both when-to-use and why.

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