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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful context beyond that: results are computed server-side from live Fortnox data and aggregated over all pages, and the comparison is against the prior-year period. It does not state how the comparison is calculated when no prior-year data exists, but that is a minor gap.

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 short sentences, with the core definition front-loaded before the example and data-source note. The API URL is somewhat incidental but does not bloat the text.

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, so return values need not be explained. Purpose, comparison basis, data freshness and aggregation scope are all covered, which is enough for an agent to invoke this correctly.

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% and each parameter already documents its meaning and default (top=25, todate=today, fromdate=fiscal-year start). The description adds no parameter-level detail, so the standard baseline of 3 applies.

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?

States a specific resource and computation: invoiced amount per customer for the period, compared against the same period last year. That clearly separates it from aggregation siblings like get_sales_by_article or list_customers. It never says it returns a ranked top-N list, though the title and 'top' parameter imply it.

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 example question ('Vilka kunder omsatte mest i år, och hur har det ändrats?') gives implied usage context for revenue-ranking questions. There is no explicit guidance on when not to use it, nor any named alternative such as get_customer or get_key_figures for single-customer or overall KPI questions.

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