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

Annotations provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds substantial behavioral context: it mentions walking the ladder, returning detailed fill data (top_of_book, vwap_fill_price, slippage_pp, etc.), and warning about forced directional risk. No contradictions.

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 lengthy but every sentence serves a purpose, covering both modes and their nuances. It front-loads the core purpose but could benefit from bullet points for the return fields and modes. Given the complexity and the need to explain two modes, it is appropriately sized and structured.

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?

No output schema is provided, so the description must fully explain return values. It does so comprehensively for both modes: lists all returned fields (e.g., top_of_book, verdict, capture_ratio, thin_legs) and explains edge cases (partial fills leading to directional risk). The description is complete given the tool's complexity.

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. The description adds value by explaining default values (size_usd=1000, side auto for basket), clarifying how size_usd is interpreted differently for single vs basket (max spend vs settlement notional), and noting the automatic side selection based on partition sum. This goes beyond the schema descriptions.

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 two modes (single-market and basket), using specific verbs like 'check', 'walk the ladder', and 'return' for each. This sets it apart from sibling tools like polymarket_arbitrage and polymarket_edges.

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: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains why partial fills can convert an arb into an unhedged position, and clarifies the requirement of either `market` or `event` parameter. No exclusion of alternatives is needed as the tool is a prerequisite for specific signals.

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