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

Annotations already declare the read-only/idempotent/closed-world profile, so the burden is lighter, yet the description adds real behavioral context: how grading is done (SNOTEL depth change clipped at zero), what bias ratio means, and the edge case that a resort with no measured series has no scores. It doesn't cover rate limits or latency, keeping it at a 4.

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 core purpose is front-loaded in the first clause, and the field-level detail that follows is largely load-bearing. It is dense and slightly list-like, but no sentence is obviously 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?

With an output schema present the description need not unpack return values, yet it explains the per-model fields, truthBasis and measuredDays, and the blend entry, making it broadly complete for a single-parameter analytical tool. The main gap is the absence of explicit guidance on when to reach for this versus sibling forecast tools.

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?

There is a single parameter with 100% schema description coverage, so the schema already documents the slug format and its source. The description adds nothing about the slug beyond what structured fields provide, which is the baseline 3.

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 names a specific resource and scope: per-model verification at a resort over 90 days plus the current 7-day forecast. An agent can immediately tell this is a model-accuracy comparison and distinguish it from resort-level siblings like compare_resorts or get_forecast.

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?

Usage is only implied — you call it to see which forecast model has verified best at a given resort. There is no explicit statement of when to prefer this over get_forecast or compare_resorts, and no exclusions. The only routing hint is the slug field pointing to search_resorts.

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