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

Annotations already mark this as read-only, idempotent, and non-destructive, and the description adds substantial behavioral detail beyond those annotations. It discloses what the tool does internally ('walks the ladder'), what outputs to expect (top_of_book, vwap_fill_price, slippage_pp, verdict), and highlights the key risk of partial basket fills becoming directional positions. No contradiction with annotations.

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 long but every sentence carries necessary information. It is front-loaded with the core purpose, then clearly structured with REQUIRES, SINGLE-MARKET, and BASKET sections. The length is justified by the tool's complexity and dual modes; it avoids fluff and redundancy.

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 has two distinct modes, no output schema, and only sparse parameter names, the description fully compensates by enumerating return fields, explaining verdicts, and detailing risk consequences. It covers inputs, outputs, constraints (size clamp), and failure modes (thin_legs, forced_directional_risk). There are no significant gaps in context.

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 description coverage is 100%, the description adds critical semantic context for each parameter. For size_usd it distinguishes between 'max spend on buys' and 'target proceeds on sells' in single-market mode, and 'settlement notional S (shares per leg)' in basket mode. It also clarifies default behavior of side in basket mode (auto from partition sum). This goes well beyond the schema.

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 and concrete purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly identifies the tool's function (risk checking) and resource (CLOB order book) and distinguishes between single-market and basket modes. It also differentiates from sibling tools by explicitly naming polymarket_arbitrage and polymarket_edges as tools it should precede.

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 gives explicit usage guidance: '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 on thin books is not capturable, partial fills create unhedged risk), and distinguishes when to use single-market vs basket mode. This is exemplary usage guidance.

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