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

Annotations already declare readOnly/openWorld/idempotent, so the bar is lower. The description adds operational detail: it walks the order-book ladder, calculates both top-of-book and VWAP fill prices, returns per-leg detail in basket mode, flags thin legs, and warns about forced directional risk from partial fills. This substantially exceeds what annotations alone convey; no contradiction exists.

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 information-dense, with each clause adding a distinct fact. It avoids filler and front-loads the core purpose. However, the single dense paragraph could benefit from bullet-structured separation of single-market vs basket modes for scannability, so a 4 rather than 5.

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?

For a tool with two operation modes, four parameters, no output schema, and significant risk implications, the description covers all bases: mode selection, parameter meanings, expected outputs, and critical usage timing. It even names the dominant loss mode. There is no obvious missing context.

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 meaning: it explains that size_usd is interpreted as max spend for buys, target proceeds for sells, and as settlement notional S (shares per leg) in basket mode. It also clarifies the default auto side selection for baskets and the clamp range. This is contextual information not present in the schema.

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 phrase 'Realizable-vs-theoretical edge check against live CLOB order-book depth', naming the exact operation and distinguishing it from sibling tools like polymarket_arbitrage that identify edges. It then enumerates concrete outputs (vwap_fill_price, slippage_pp, verdict) that make the purpose unmistakable.

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 instructs to 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500', naming exact sibling tools and providing a threshold. It also explains the failure mode it prevents, giving when-not-to-skip guidance. No alternative is needed beyond this clear directive.

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