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

The description reveals behavioral details beyond annotations: the Jaccard similarity threshold, placeholder filtering rules, partition-check sum expectations, and the fill check logic that warns "do not trade it" if the edge is not realizable. This adds significant context on how the tool behaves in various scenarios.

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 well-structured with clear sections for modes, semantic anchor, partition filter, response format, and fill check. It is front-loaded with the core purpose and immediately explains the no-arg vs event vs topic options. Some details, like the exact Jaccard threshold, may be more than needed but add depth without being wasteful.

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's complexity and the lack of an output schema, the description thoroughly covers response shapes, edge cases (e.g., placeholder fractions), and how to interpret results (realizable_edge_pp ≤ 0 means don't trade). It also points to a sibling tool for related but distinct functionality, ensuring the agent understands the full 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?

The description provides rich semantic meaning for both parameters event and topic, with concrete slug examples and explanations of what each mode does. It also covers the no-arg behavior, which is essential since the schema marks no parameters as required but the tool has a meaningful default action.

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 and resource: "Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks." It clearly distinguishes from sibling tools like polymarket_edges, polymarket_edge_tracker, and polymarket_fill_risk by focusing on arbitrage detection methods.

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 usage guidance is provided: "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 differentiates when each mode is appropriate and references a sibling tool for custom sizing, giving clear when-to-use and when-not-to-use direction.

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