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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description goes far beyond this by detailing input requirements (one of market or event), default values (size_usd default 1000, side default), output fields (top_of_book, vwap_fill_price, slippage_pp, etc.), and the risk of partial basket fills converting an arb into an unhedged directional position. It also explains size_usd interpretation per mode. No contradiction 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 long but well-structured with all-caps section markers (REQUIRES, SINGLE-MARKET, BASKET, USE THIS) and a clear one-sentence opening definition. It is front-loaded and scannable. Some redundancy exists (e.g., the thin-book risk warning repeats the earlier 'theoretical overround on thin books' concept), but the length is largely justified by 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?

With no output schema, the description thoroughly lists return fields for both modes (e.g., top_of_book, vwap_fill_price, slippage_pp, verdict for single-market; theoretical_sum, realizable_sum, capture_ratio, thin_legs, forced_directional_risk for basket). It also covers edge cases (partial fills, thin books), provides a size threshold ($500), and explains the verdict categories. This is complete for a complex tool.

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% with detailed parameter descriptions, so the baseline is 3. The description adds mode-specific context not fully present in the schema, such as how size_usd is interpreted differently in single-market ('max spend on buys, target proceeds on sells') versus basket ('settlement notional S') modes, and clarifies valid parameter combinations. While much of the parameter info is repeated from the schema, the mode integration adds meaningful selection guidance.

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 and resource: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It then clearly delineates two modes (SINGLE-MARKET and BASKET) and explicitly names sibling tools (polymarket_arbitrage, polymarket_edges) to differentiate its role as a pre-trade validation tool. This is a specific, well-scoped purpose.

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?

The description explicitly instructs when to use this tool: '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 directional positions) and provides mode-selection requirements ('REQUIRES one of market or event'). This is exemplary usage guidance.

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