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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: data source (SNOTEL station readings), the normal baseline used (1991–2020 median for today's date), inclusion thresholds (10–300% band, >2 in SWE), the sort order, and what is deliberately withheld from the ranking.

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?

Purpose and metric definition are front-loaded in the first clause, and the qualification rules are packed efficiently into the second. Dense with semicolons but no clearly wasted sentence; only the trailing marketing URL is dispensable.

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 an output schema present, the description needn't explain return values, and the annotations cover the safety profile. What remains an agent needs — metric definition, sort order, filtering thresholds, and geographic scoping — is all present.

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 both parameters are already documented in the schema; baseline 3 applies. The description only restates state scoping ('optionally within one state') and says nothing about the limit parameter or its default/ceiling, adding little 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?

States a specific verb+resource+ordering: 'SNOTEL-fed resorts ranked by snowpack relative to normal... deepest first, optionally within one state.' The definition of the metric (SWE vs the station's 1991–2020 median for today's date) distinguishes it clearly from siblings like get_snow_history and compare_resorts.

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?

Gives clear decision context: measurement-based ranking, optional single-state scoping, and explicit exclusion rules ('early-season noise is withheld, not ranked') that tell the agent when results will be thin or empty. It does not name an alternative sibling (e.g. compare_resorts, get_snow_history) or state when-not to use it, so it stops short of a 5.

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