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

With no annotations, the description carries the behavioral burden, and it discloses key traps: an omitted co2 is read as battery-electric and 'collapses the tax to near zero with no error raised.' It also states the result is an estimate, not an official Motorstyrelsen valuation, and that the engine matches bildata.io's public calculator. It does not describe return shape or side effects, though this is a pure calculation tool.

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 long but earned: every sentence adds a constraint or context needed for correct invocation, from the required new/used pairs to the co2 trap to the JSON-number rule. Critical warnings are front-loaded and highlighted with 'REQUIRED PAIRS' and 'ALWAYS,' making the text dense but efficient for a 17-parameter tool.

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?

For a complex 17-parameter tool with no annotations and no output schema, the description covers the most dangerous input behaviors, conditional requirements, and value semantics. Missing items are explicit routing against forecast_registreringsafgift and any direct description of the response object, though the tool name and 'calculate tax' make the primary output inferable.

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%, so the baseline is 3, but the description adds meaning beyond each property's schema entry: it defines required pairs across parameters, clarifies that nypris is the used vehicle's own original price and not the new-vehicle price field, and warns that omitted co2 is treated as 0. This cross-parameter and serialization guidance is genuinely additive, though individual parameters are already well documented in the schema.

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 names a specific verb ('Calculate'), a precise resource ('Danish vehicle registration tax (registreringsafgift)'), and the eligible vehicle types ('personbil, varebil or motorcykel'). It also situates the calculation under 'registreringsafgiftsloven' and distinguishes it from siblings like forecast_registreringsafgift by being the direct calculation tool.

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?

It gives explicit conditional guidance: condition='new' requires bruttovaerdi, condition='used' requires handelspris and nypris, and co2 must always be sent for fuel-burning vehicles. It also instructs on JSON number formatting, enum use, and omitting unknown optional fields. It does not explicitly state when to prefer this over sibling tools such as forecast_registreringsafgift, so it stops short of full alternative routing.

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