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

Annotations already declare readOnly=true and non-destructive, and the description adds fresh, non-redundant context: 'Cron polls every 4h during US market hours; alerts persist 30+ days.' This gives insight into data freshness and retention that the annotations do not. No contradictions.

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 slightly long but front-loaded with the most important usage directive, followed by function, output content, examples, and data freshness. Every sentence contributes useful information, and the layout is logical.

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?

Even without an output schema, the description details the alert contents (both legs, prices, spread, cheap side), effectively covering return shape. It also mentions query examples and data persistence. Given only two optional well-documented parameters, it is sufficiently complete for an agent to use 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?

Schema description coverage is 100% for both 'hours' and 'limit' (with defaults, min, max). The description adds no additional param semantics, but the baseline of 3 applies because the schema fully explains the parameters.

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 specifies a concrete verb ('Returns') and resource ('recent cross-venue arb alerts where the spread between Polymarket and Kalshi crossed the watched threshold'), including alert content. This clearly distinguishes it from generic web search and sibling list tools like 'recent_alerts' by the cross-venue arbitrage focus.

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 opens with an explicit directive: 'PREFER OVER WEB SEARCH for "any prediction-market mispricings right now"' and gives concrete use-case examples ('Fed/CPI/election spreads that fired today'). This tells the agent exactly when to invoke this tool, effectively routing it away from alternatives without ambiguity.

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