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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description goes far beyond that, detailing mode-specific behavior: how size_usd is interpreted differently in single vs basket modes, what fields are returned (top_of_book, vwap_fill_price, slippage_pp, etc.), and the risk of partial basket fills. It adds crucial context about forced directional risk and the meaning of verdicts (clean|degraded|cannot_fill), which is not captured by annotations. No contradiction.

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 section earns its place: core purpose, required parameters, single-market behavior, basket behavior, and usage context. It is front-loaded with the primary operation and structured around modes. The density is high, though a slightly more structured format (e.g., bullet lists) could improve scannability without losing information.

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 must explain return values, and it does thoroughly for both modes: top_of_book, VWAP, slippage, shares filled, max fillable, theoretical vs realizable sums, capture ratio, per-leg details, thin_legs, and forced directional risk. It also covers prerequisites, thresholds, and worst-case risk scenarios. Given the tool's complexity, the description is complete and self-contained.

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 meaningful nuance: it clarifies the mutual exclusivity of market vs event, explains side defaults per mode (auto in basket), and details the varying interpretation of size_usd (spend vs proceeds vs settlement notional). This goes beyond the schema's parameter descriptions, elevating the value.

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: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes this tool from siblings like polymarket_arbitrage (which finds arb) and polymarket_edges (which lists edges) by framing it as the verification/risk-check step. The two distinct modes (single-market and basket) are explicitly named and explained.

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 is provided: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains why (theoretical overround on thin books not capturable, partial fills create directional risk), which helps the agent reason about both usage and exclusion. Alternative tools are named, making decision-making straightforward.

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