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

The description is extraordinarily transparent about behavior beyond annotations. It discloses the Jaccard similarity threshold (≥0.30), partition filter rules (>20% placeholder fraction returns null), fill check mechanics against live CLOB depth, and the interpretation of realizable_edge_pp ≤ 0 (do not trade). This far exceeds the readOnlyHint/openWorldHint/idempotentHint annotations by adding critical domain logic.

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 it is well-structured with clear sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and front-loaded with the core purpose and argument patterns. Every sentence adds substantive value (thresholds, examples, output details), making it dense rather than wasteful. However, it is not as minimal as the top-tier example; a few details could be streamlined without loss.

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?

Despite having no output schema, the description fully compensates by describing the response shape ('opportunities[] with gap_pp, suggested_trade, reasoning...') and including edge cases like thin_legs and skipped_low_similarity. It also contextualizes when to combine with polymarket_fill_risk. For a complex tool with 2 optional parameters, this is complete.

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% for both parameters, and the description goes far beyond the schema. It provides examples of valid values ('fed-decision-may-2026', 'when-will-bitcoin-hit-150k'), explains full Polymarket URLs are accepted, and details the distinct behavior for each mode (event vs topic), including what types of insights each yields. This enriches both parameters considerably.

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+method: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly distinguishes itself from sibling tools by detailing unique mechanisms (monotonicity, partition-check, trending scan) and explicitly names alternative tools for different tasks (e.g., polymarket_fill_risk for sizing).

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 mode selection: '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 also points to an alternative tool: 'For custom sizing use polymarket_fill_risk.' However, it does not fully delineate when not to use this tool versus other edge-finding siblings like polymarket_edges or polymarket_kalshi_spread, so it falls short of a perfect 5.

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