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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the tool is safely read-only and idempotent. The description adds substantial behavioral context: it explains the underlying model (how amortization is treated as savings, how the renter's down payment earns ISK returns, four Swedish rules that are applied, and one-time costs by property type). This goes well beyond annotations, though it does not discuss rate limits or error conditions.

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 quite long and dense, with multiple clauses and examples. While front-loaded with trigger phrases, it includes several sentences that could be trimmed. The core routing information is present, but the explanation of Swedish rules, though valuable, makes it less concise than optimal for a tool description.

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?

The description provides a complete picture for an agent to call the tool correctly: it defines the decision context, warns about a common pitfall, outlines the four key Swedish rules, explains the output structure (a 'svar' field and a 'lankAttVisaAnvandaren' link to include), and specifies the scope (Sweden, 2026, SEK, percentages). With an output schema present, it does not need to detail return values further, and it covers all necessary caveats and instructions.

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 schema already documents all 15 parameters with defaults and ranges. The description adds extra value by explaining the key modeling assumptions: amortization is savings, the renter invests the same capital, and the down payment percentage interacts with Swedish mortgage rules. It also implies that interest rates and returns are entered as percentages (e.g., 2.7 for 2.7%), which is already in the schema but reinforced.

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 trigger phrase ("Anropa detta verktyg när någon överväger att köpa en bostad i Sverige och undrar om det lönar sig") and lists concrete user questions it answers, including "ska jag hyra eller köpa" and "lönar det sig att köpa lägenhet". This clearly distinguishes it from siblings like forhandla_bolaneranta (mortgage rate negotiation) and sparmal_isk_vs_sparkonto (savings goals), which address different decisions.

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 when-to-use triggers are provided via example questions. The description also includes a critical warning not to do a naive monthly-cost comparison, which is a specific usage guideline to avoid a common error. It states scope restrictions (only Sweden, only 2026 tax rules, not about loan promises or creditworthiness).

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