get_weather_warnings

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

The description adds meaningful behavioral context beyond the annotations: it returns all active warnings tagged by county/area, supports filtering by county and severity, defines the severity ordering (RED > ORANGE > YELLOW > MESSAGE), and discloses the error behavior (returns isError: true if the API is unreachable). This is rich context for a read-only tool with already-safe 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 five sentences long, but every sentence earns its place: main purpose, non-coordinate/filtering model, severity ordering, explicit sibling guidance, error behavior, and geographic coverage. It is front-loaded with the primary action and resource, making it easy to scan, with no filler or redundant statements.

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?

Despite having no output schema, the description provides sufficient information for correct invocation and interpretation: it explains that results are active warnings tagged by area, how to narrow them, severity levels, error cases, and coverage. Given the tool's moderate complexity and strong annotations, this is complete enough for an agent to select and call the tool appropriately.

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 schema provides 100% coverage with detailed descriptions for all three parameters, including the case-insensitive substring match for county, the language enum, and the severity threshold ordering. The description restates some of this (e.g., 'filter by county name and/or minimum severity') but does not add meaning beyond the schema. Thus 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 opens with a specific verb and resource: 'Get currently active official SMHI weather warnings/alerts for Sweden.' It further distinguishes itself from siblings by stating it is 'not coordinate-based' and lists the types of impact-based warnings covered. This makes the tool's purpose unambiguous and clearly differentiated from the forecast and fire-risk tools.

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?

Explicit usage guidance is provided: 'Use this for "is there a storm warning" type questions; use the forecast tools for general future conditions and get_fire_risk for the underlying fire danger index.' It also clarifies the tool is limited to Sweden, which helps agents avoid misuse. This goes beyond implied usage to explicitly state when to use and when to use alternatives.

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