compare_locations

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

No annotations exist, so description carries the burden. It discloses a key behavioral trait: when scanning all Switzerland, only extremes and summary statistics are returned. It also suggests workarounds. However, it does not detail what 'total tax burden' includes or other side effects, but for a read tool this is sufficient.

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: purpose, use case, and limitation/workaround. Every sentence earns its place, with no wasted words. The structure is front-loaded with the core purpose.

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 tool's complexity (16 params, no annotations, has output schema), the description covers the essential: what it does, limitations, and how to narrow. It relies on output schema for return format. It is mostly complete but could mention what 'total tax burden' encompasses (e.g., all levels of tax).

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 38%, low, so description should compensate. It adds meaning by explaining that `scope` and `only_cantons` narrow results, but it does not elaborate on income, wealth, or other household parameters. The description provides high-level context but lacks depth for many parameters.

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 clearly states the tool ranks municipalities by total tax burden for a household, answering 'where would I pay the least?'. It uses specific verbs ('rank') and resource ('municipalities'), and distinguishes from siblings by focusing on comparison across all of Switzerland, with nods to sibling tools like 'find_cheapest_nearby' implicitly via scope limitations.

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 tells when to use (to find least tax location) and provides explicit guidance on limitations: scanning all 2100 municipalities returns only extremes and summary stats, so narrow with `scope` or `only_cantons`. It lacks explicit comparisons to siblings but implies usage context well.

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