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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds deep behavioral context: 'walks the ladder', enumerates specific outputs (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict), and warns about 'partial basket fills convert an arb into an unhedged directional position.' This far exceeds the annotation baseline and provides critical risk context.

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 earns its place: it explains two modes, their parameters, return fields, and usage context. It uses clear visual structure (caps for mode names, semicolon-separated lists) and contains zero filler. The density is justified by 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?

With no output schema, the description carries full responsibility for explaining returns, which it does thoroughly: it lists single-market outputs, basket outputs, special cases (thin_legs, forced_directional_risk), and the verdict enum. It also covers defaults, size interpretation, and failure risk. Nothing important is missing for an advisory 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?

Although schema coverage is 100%, the description adds crucial mode-dependent meaning: `side` values differ between single-market (buy_yes|sell_yes|buy_no|sell_no) and basket (sell_yes|buy_yes with auto default), and `size_usd` is interpreted differently ('max spend on buys' vs 'settlement notional'). This complements the schema and prevents misuse.

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 precise, specific verb-resource-scope statement: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly names the two operating modes (single-market and basket) and differentiates from sibling tools by explicitly positioning itself as a pre-trade check before acting on arbitrage signals.

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?

Provides explicit usage criteria: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also gives a threshold-based exclusion (below ~$500), and explains which mode to choose via `market` vs `event`. This is clear when-to-use and when-not-to-use guidance.

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