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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds substantial behavior beyond that: limit clamping (1-25, default 10, floors fractions, echoes effective limit), output fields (address, capacity, distance), the absence of a municipality field, and the no_coverage response for out-of-range coordinates. No contradiction with 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 a single dense paragraph of about 120 words, with the core purpose front-loaded and each subsequent sentence providing necessary detail or a caveat. The closing emergency note is slightly tangential but still useful; the density is high but not wasteful.

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?

Given the rich annotations and presence of an output schema, the description still adds all invocation-relevant information: parameter behavior, coverage bounds, no_coverage status, and an explicit alternative sibling. An agent can correctly select and call the tool without further clarification.

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 description coverage is 100%, but the description enriches the parameters by explaining the limit default and floor/echo behavior and by clarifying the effective coordinate bounds for lat/lng. It also adds semantic context that the address serves as the location identifier since there is no municipality field.

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 'Find the nearest Swedish civil-defence shelters (skyddsrum) to a WGS84 position, sorted by distance' — a specific verb, resource, and ordering. It also explicitly names search_location as an alternative for place-name input, distinguishing it from at least one sibling.

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?

Explicitly instructs 'Use search_location first if you only have a place name', giving a clear when-to-use vs when-not-to-use condition. It also states Sweden-only coverage and the resulting 'no_coverage' status for out-of-range positions, which helps agents decide whether to call this tool.

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