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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds behavioral context beyond that: it discloses the small sample size ('n=3 disclosed'), the interpretive caveat ('A pattern, not a promise'), and the nature of D/E tiers as timing plays. It also specifies that the output includes a methodology note and an in-season scorecard when live, which clarifies data freshness. This is valuable added transparency without contradicting annotations.

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 three sentences and efficiently packs the essential information: what it does, what it returns, when to use it, and a caveat. It front-loads the core purpose and output list, with the usage rule and caveat following. It is not overly verbose for the amount of content it conveys, though the list of outputs is a bit dense. Overall well-structured and appropriately sized.

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?

The tool has an output schema, so return structure is already defined. The description supplements with specific output elements (rank, tier, analog winters, forecast paragraph, methodology note, scorecard) and includes important caveats about data limitations (n=3, pattern not promise). For a read-only, idempotent tool with a clear usage rule and output schema, the description is sufficiently complete for an agent to decide when and how to use it.

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% — both slug and resort are fully described in the input schema, so the agent already knows their meaning and format. The description only refers to 'a named resort', which reiterates that the parameter identifies a resort but adds no new semantics beyond the schema. With complete schema coverage, the baseline of 3 is appropriate.

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 states a clear, specific purpose: it returns a resort-level El Niño/ENSO outlook from a defined dataset (SnowSure's 30-year fleet, 559 resorts). It lists the concrete outputs (rank, tier, signals, analog winters, forecast paragraph, methodology note, scorecard), which precisely defines the tool's scope. It distinguishes from siblings by explicitly targeting 'a named resort', which separates it from the ranking-oriented get_elnino_rankings.

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 gives an explicit usage rule: 'Use for ANY El Niño, ENSO, or 2026-27 winter-outlook question about a named resort.' This clearly tells an agent when to invoke this tool. However, it does not explicitly mention when not to use it or name alternative sibling tools (e.g., get_elnino_rankings for fleet-wide rankings), so it lacks explicit exclusions, but the context strongly implies the distinction.

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