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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as true/false. The description adds significant behavioral context: it walks the order book, returns detailed fields (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict), and warns about partial basket fills converting arb into unhedged directional positions. This goes well beyond what annotations convey.

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 front-loaded with the core purpose and uses clear section headings (SINGLE-MARKET, BASKET) and emphasis (REQUIRES, USE THIS). It is verbose but each sentence adds necessary detail. The structure is effective for an agent parsing key points. Could be slightly tighter, but overall well-organized.

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, many output fields), the description covers all essential information: input modes, parameter behavior, expected outputs, and critical warnings about partial fills and directional risk. There is no output schema, so the description bears full burden and meets it comprehensively.

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%, so baseline is 3. The description adds value by explaining how parameters behave differently in single-market vs. basket mode, such as size_usd being interpreted as settlement notional for baskets, and side defaulting to auto based on partition sum. However, the schema already has reasonable descriptions, so the additional semantics are useful but not extensive. Score 4 reflects good supplementary context.

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: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It distinguishes between single-market and basket modes with specific verbs and parameters, and explicitly differentiates from siblings by stating 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.'

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 context: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains why (theoretical overround not capturable, partial fills cause directional risk) and implies when not to use (when trades are small or theoretical edge is capturable). No explicit alternatives are named, but the reference to sibling tools in context is sufficient.

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