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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, but the description adds substantial behavioral detail beyond those: it discloses live CLOB depth fill-checking, specific thresholds (3pp deviation, 0.30 Jaccard similarity, 20% placeholder fraction), and the condition where realizable_edge_pp ≤ 0 means 'do not trade it'. It also mentions skipped_low_similarity and null signals, offering transparency without contradicting 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?

Despite being long, the description is well-structured with uppercase section headers (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and clear mode subheadings. Every sentence delivers operational detail, such as thresholds, response fields, and edge cases, with no repetition or filler. It is front-loaded with the core purpose and then systematically expands, making the length appropriate for 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 a heavy burden to explain returns, and it does so thoroughly: it specifies the response structure (opportunities[] with gap_pp, suggested_trade, reasoning, monotonicity context) and the partition_check fields in event mode. It also covers failure and edge cases (placeholder filters, low-similarity rejections, thin legs), leaving no ambiguity for an agent to invoke the tool correctly.

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 provides descriptions for both event and topic parameters, achieving 100% coverage, which sets a baseline of 3. The description enriches this by explaining the full behavior of each mode: event walks child markets and checks date/threshold ordering, while topic searches related events and flattens markets. It also notes that full Polymarket URLs are accepted, adding value 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, actionable statement: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly identifies the resource (Polymarket), the action (find arbitrage), and the method. It also distinguishes itself from sibling tools like polymarket_edges and polymarket_fill_risk by detailing distinct modes (trending_scan, event, topic).

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 instructions for each mode: 'Call with NO args for a trending_scan', 'event (recommended for a specific market)', and 'topic (for cross-event scanning)'. It also names an alternative tool for custom sizing: 'For custom sizing use polymarket_fill_risk.' This is clear when-to-use/not-use guidance, exceeding a typical description.

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