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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds substantial behavioral context: mode selection (market vs event), default parameter behaviors, return verdicts (clean|degraded|cannot_fill), and risk disclosure 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 dense but well-structured with clear sections (SINGLE-MARKET, BASKET) and front-loaded purpose. Every sentence adds value, covering mode specifics, return fields, and risk warnings. However, it could be slightly more concise for faster scanning, but the detail is justified given 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?

Despite lacking an output schema, the description explicitly lists all return fields for both modes, explains edge cases (thin legs, partial fills), and provides risk context (forced directional risk). It covers all critical aspects for correct usage, including parameter defaults and behavioral constraints.

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 meaning beyond schema by explaining how parameters interact in each mode (e.g., size_usd interpreted as settlement notional for basket, side default auto from partition sum). It provides context for interpretation that the schema alone does not convey, such as 'capture overround' and 'max spend on buys, target proceeds on sells'.

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 purpose as a realizable-vs-theoretical edge check against live CLOB order-book depth. It distinguishes between single-market and basket modes, lists specific return fields (top_of_book, vwap_fill_price, etc.), and differentiates from sibling tools like polymarket_arbitrage and polymarket_edges through explicit usage guidance.

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 when-to-use guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'. It also explains when not to rely solely on theoretical overround ('theoretical overround on thin books is not capturable') and warns about risks of partial fills converting arb into unhedged directional positions. This satisfies both positive and negative usage contexts.

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