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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered. The description adds substantive behavioral detail beyond annotations: it walks the order-book ladder, returns specific metrics (top_of_book, vwap_fill_price, slippage_pp), and warns about partial fills converting an arb into unhedged directional position. This is rich context that complements the annotation-provided safety profile.

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 (~200 words) but every sentence earns its place, covering two distinct modes, required vs optional parameters, return fields, and risk warnings. It is front-loaded with purpose and then structured around modes, making it scannable. However, it could be split into shorter paragraphs or bullet points for even easier parsing, so it's not perfect on 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?

The tool has no output schema, so the description carries the full burden of explaining return values. It does this thoroughly: listing both single-market and basket outputs, including field names like `capture_ratio`, `thin_legs[]`, and `forced_directional_risk`. It also provides temporal context (when to use) and the failure mode ('partial basket fills convert an arb into an unhedged directional position'). Given the tool's complexity, this is very complete.

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. But the description adds significant meaning beyond the schema: it explains how `size_usd` is interpreted differently in single-market ('max spend on buys, target proceeds on sells') vs basket ('settlement notional S — shares per leg, each paying $1'), and how `side` auto-selects in basket mode. These semantics are not evident from the parameter descriptions alone.

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+resource: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It immediately distinguishes itself from sibling tools like polymarket_arbitrage and polymarket_edges by focusing on fill risk and book depth, not signal generation. The two modes (single-market and basket) are clearly named and described.

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?

Explicit when-to-use guidance is given: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains the rationale ('theoretical overround on thin books is not capturable') and distinguishes between single-market and basket modes, providing clear decision context.

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