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

Annotations (readOnlyHint, etc.) are present, but the description adds significant behavioral context: it walks the order book ladder, returns specific fields (top_of_book, vwap_fill_price, slippage_pp, verdict), and warns about forced_directional_risk and thin_legs. 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 justified given the tool's complexity (two modes, many return fields, usage guidance). It is well-structured with clear sections (SINGLE-MARKET, BASKET) and lists return fields. While every sentence adds value, a minor reduction in verbosity could improve conciseness.

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 the tool's complexity (two modes, multiple parameters, no output schema), the description is remarkably complete: it enumerates all return fields, explains the verdict levels (clean|degraded|cannot_fill), and warns about pitfalls (thin_legs, forced_directional_risk, partial fills). It covers everything an agent needs to understand behavior and results.

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 substantial semantic detail beyond the schema: explains the difference between market and event modes, how size_usd is interpreted differently (spend vs target proceeds vs settlement notional), default behaviors (auto side for basket), and clamps. This greatly aids correct parameter usage.

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 states the tool's function: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It distinguishes between single-market and basket modes, uses specific verbs (walks, returns), and mentions key resources (market, event). Sibling tools like polymarket_arbitrage are explicitly referenced, aiding differentiation.

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: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It provides rationale—theoretical overround on thin books is not capturable, and partial fills create directional risk—which helps the agent decide when not to rely solely on theoretical signals.

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