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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructive=false, and the description adds deeper behavioral detail: it 'walks the ladder,' returns a verdict (clean|degraded|cannot_fill), identifies thin_legs and forced_directional_risk, and warns about partial basket fills converting arb into unhedged directional positions. This goes far beyond the annotations, explaining the tool's operational logic and failure modes.

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?

Though long, the description is tightly structured with uppercase section labels (REQUIRES, SINGLE-MARKET, BASKET, USE THIS) and every sentence carries unique information. It front-loads the core purpose in the first clause and packs no filler.

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?

With no output schema, the description compensates by enumerating all return fields per mode (top_of_book, vwap_fill_price, slippage_pp, capture_ratio, profit_usd, thin_legs[], etc.) and explains the risk context. It fully covers the tool's behavior, inputs, and the consequences of partial fills, making it complete for a complex analysis tool.

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?

The schema already provides 100% parameter descriptions, but the tool description adds crucial semantics: the REQUIRES one of market/event constraint (absent from schema, where all are optional), the interpretation of size_usd as settlement notional in basket mode, and the default auto behavior for side. It also explains the clamping range and per-mode meanings, making the parameters unambiguous.

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 pairing: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes single-market and basket modes, and explicitly positions it relative to sibling tools (polymarket_arbitrage, polymarket_edges). This leaves no ambiguity about what the tool does.

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 it: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains the two modes and provides context about why it's necessary (theoretical overround on thin books is not capturable). There is clear guidance on prerequisites, though it does not enumerate when not to use it, which is acceptable given its role as a prerequisite check.

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