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

Annotations declare readOnly, openWorld, idempotent, and non-destructive. The description adds substantial behavioral detail beyond that: it walks the order-book ladder, returns a verdict (clean|degraded|cannot_fill), identifies thin legs, reports max_fillable_usd and forced_directional_risk, and warns about partial basket fills. This gives the agent a concrete model of what the tool inspects and what risks it flags.

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 carefully structured with uppercase mode labels (SINGLE-MARKET, BASKET), a clear progression from purpose to parameters to outputs to usage timing. Every sentence adds a distinct piece of information, and the first sentence immediately states the core function. The density is justified by the tool's complexity and high-stakes financial context.

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?

There is no output schema, so the description must enumerate return values; it does so comprehensively (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict, capture_ratio, profit_usd, thin_legs, max_clean_notional_usd, forced_directional_risk). It also covers both modes, parameter defaults, and rationale for use versus siblings. For a complex financial tool with no output schema, this is 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?

The input schema already describes all 4 parameters (100% coverage), but the description goes further. It clarifies the distinct semantics of `size_usd` in single-market mode (spend vs target proceeds) versus basket mode (settlement notional per leg), explains the default side auto-selection in basket mode, and explicitly ties `market` to single-market and `event` to basket mode. This is far beyond baseline schema repetition.

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-noun purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes from siblings like polymarket_arbitrage and polymarket_edges by focusing on fill risk rather than edge discovery, and it explains the two modes (single-market vs basket) with concrete examples.

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 usage guidance is provided: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It names sibling tools and explains why (theoretical overround on thin books is not capturable, partial fills convert arb into directional risk), giving clear when-to-use and why-not-to-skip guidance.

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