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

Annotations already declare readOnlyHint, idempotentHint, and non-destructiveHint, so the safety profile is covered. The description adds significant behavioral context beyond this: it walks the order book ladder, returns specific fields like slippage, and highlights the risk of forced directional risk in basket mode. It also explains the interpretation of size_usd differently for buys vs sells. This is comprehensive but the annotation coverage reduces the burden somewhat.

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 well-structured with clear sections for single-market and basket modes, and a concluding usage note. It's front-loaded with the core purpose. However, it is somewhat verbose; some details (like default values) could be left to the schema. The length is justified by the tool's complexity, but it could be trimmed slightly without losing meaning.

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 no output schema, the description comprehensively lists all return fields for both modes, including edge cases like thin_legs and forced_directional_risk. It explains the verdict categories and the risks of partial fills. The description is complete for the tool's complexity (4 parameters, two modes), with no apparent gaps. It even includes domain-specific guidance about the dominant loss mode in arb-bot P&L.

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 description coverage is 100%, but the description adds important semantic details: it explains how side defaults differ between single-market and basket modes, and how size_usd is interpreted (spend vs proceeds vs settlement notional). For the event parameter, it clarifies it triggers basket mode and checks every leg. This goes beyond the schema descriptions, making the parameters clearer.

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 defines the tool as a 'Realizable-vs-theoretical edge check against live CLOB order-book depth' and distinguishes between single-market and basket modes. It explicitly contrasts with sibling tools like polymarket_arbitrage and polymarket_edges, stating when to use this tool (before acting on those signals) and when not to (small trades).

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 provides explicit usage conditions: 'REQUIRES one of market or event', and explains the two modes. It gives clear guidance on when to use the tool ('USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500') and warns against partial fills converting arb into unhedged positions, effectively stating when not to use. This provides excellent context for agent decision-making.

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