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

The description goes far beyond the readOnlyHint/openWorldHint/idempotentHint annotations by detailing the internal checks (partition-sum >3pp, Jaccard similarity ≥0.30, placeholder filters) and the critical fill-check caveat: 'realizable_edge_pp ≤ 0 means the overround exists only at last-trade, not in the book; do not trade it.' This level of nuance is essential for safe use and is fully consistent with the 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 dense and information-rich, but it is somewhat long and could benefit from clearer paragraph separation. Each sentence does contribute unique value—mode guidance, semantic anchors, partition filter, fill check—so it avoids fluff. The use of ALL CAPS section headers aids scanning, earning it a 4 rather than a 3.

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 fully compensates by detailing the response structure: 'opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context)' and the event-mode partition_check fields. It also explains the fill-check pricing mechanism and its interpretation. This is a complex tool, and the description leaves little ambiguity about its operation and results.

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 the schema already provides 100% parameter coverage, the description adds substantial meaning. It explains that 'event' triggers a child-market walk and partition_check, while 'topic' performs a cross-event search with semantic anchoring. Concrete examples ('fed-decision-may-2026', 'Strait of Hormuz traffic returns to normal') and the mode-specific output structures give the agent a deeper understanding of how each parameter changes behavior.

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: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly distinguishes this from sibling tools like polymarket_edges (which focuses on edges) and polymarket_fill_risk (which handles fill risk), ensuring the agent knows exactly what this 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 provides explicit when-to-use guidance: 'Call with NO args for a trending_scan... pass event for the strongest per-event partition_check, or topic for a themed cross-event scan.' It even recommends event mode for a specific market and explains how cross-event mode catches patterns single-event misses. It also directs users to polymarket_fill_risk for custom sizing, effectively stating when not to use this tool.

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