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

Annotations already mark the tool readOnly, idempotent, and non-destructive. The description goes further by explaining that the data is forecast-only, that events carry a confidence tier (watching / likely / locked), and that returning no events is the normal state outside a storm cycle. This adds meaningful behavioral context beyond the annotation flags.

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 front-loaded with what the tool returns, then gives example use cases, then explains the forecast/observation distinction and the empty-state behavior. Despite using a few sentences, every sentence adds information an agent needs for correct selection and interpretation; there is no filler.

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 output schema already covers return fields, the description covers the remaining contextual needs: when to use it, what the events represent, what confidence tiers exist, how results are ordered, the forecast-vs-observation distinction, and the normal empty result. The tool is self-sufficient for correct invocation and interpretation.

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%, so the baseline is 3. The description adds value beyond the schema by clarifying that 'events' are storm systems spanning multiple resorts, which gives semantic meaning to the limit parameter, and by noting events are ranked biggest first. This is useful context the schema alone does not fully convey.

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 gives a concrete verb and resource: it returns named multi-day storm systems flagged days ahead, grouped as one event across resorts and ranked by size. It clearly distinguishes this from observation-based tools by explicitly saying FORECAST, NOT OBSERVATION, and by naming get_snow_report and find_best_powder as the alternatives for snow that has already fallen.

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?

It provides explicit example queries ('is a storm coming', 'what's the next big system', 'where will it dump this week') and explicitly states when not to use it: for snow that already exists, use get_snow_report or find_best_powder. This gives an agent clear routing criteria.

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