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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint). The description adds genuinely useful behavioral context beyond them: the scoring is cross-validated ('scored without using the station being scored'), drawn from a fixed station panel across terrain types, and benchmarked against a single-model baseline. It does not mention cost, rate limits, or how fresh the record is.

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?

A single sentence that front-loads the core purpose and packs the metric definitions into its subordinate clauses. It is dense and slightly run-on, but every clause carries information (metrics, station panel, validation method, baseline) and nothing is 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 no parameters and no output schema, the description must carry the return-value burden, and it does specify the metrics reported (high/low error by lead day, Brier score, station panel, baseline comparison). It omits the time window the record spans and any framing of output shape, which are the remaining gaps.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies a no-argument call.

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 capability: Veabird's historical point-forecast accuracy, broken down into average daily high/low error by lead day and a Brier score for rain/snow probability. This clearly separates it from point_forecast (the forecast itself) and from sargassum_model_skill (a different domain's skill metric). It never explicitly names a sibling to route against, so it stops short of a 5.

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?

Implied usage is discernible — consult this when you want evidence of how reliable Veabird's forecasts are versus a typical weather-app model — but there is no explicit when/when-not statement, no prerequisites, and no named alternative for obtaining similar validation. Adequate but with a clear gap.

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