compare_locations

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It usefully reveals that only the extremes plus summary statistics are returned for full-Switzerland scans, which is genuine added value. However, it doesn't disclose behavior for narrow scopes, authentication needs, or how the summary statistics are composed, leaving gaps for a tool with zero annotation cover.

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?

Three sentences, front-loaded with the core purpose, followed by the behavioral caveat and the narrowing advice. Efficient and orderly, though the second sentence is somewhat dense. No redundant 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?

An output schema exists, covering return values, and the core purpose plus narrowing workflow is clear. But with 16 parameters and only 38% schema coverage, the description does not explain how the household is assembled (which fields belong to person 1 vs person 2, what children_ages or relationship drive), leaving meaningful ambiguity for a complex input set.

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 only 38% across 16 parameters, so the description should compensate — but it only references `scope` and `only_cantons`. The household parameters (income1/2, age1/2, confession1/2, children_ages, relationship) and income_type fields are left entirely unexplained, so an agent cannot correctly structure a household input from this definition.

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 specific verb (rank), resource (municipalities), and basis (total tax burden for one and the same household), and explicitly frames the question it answers ('where would I pay the least?'). It is clearly distinct from siblings like calculate_tax and find_cheapest_nearby, so an agent can select it without ambiguity.

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?

Provides explicit guidance on the default full-Switzerland scan (~2100 municipalities) and instructs narrowing with `scope` or `only_cantons` to target a specific region or canton. It communicates when the result set is restricted, though it does not name a specific alternative tool to prefer in other cases.

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