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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds real value beyond that: results are computed server-side from live Fortnox data and are aggregated "over all pages", which tells the agent pagination is already handled and the figures are current rather than cached.

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?

Purpose is front-loaded in the first clause, followed by an example and provenance in a compact three-sentence block. The Fortnox API URL is marginally useful decoration but does not bloat the definition meaningfully.

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?

With an output schema present and full parameter documentation, the description only needs to orient the agent, which it does via purpose, example, and data provenance. The remaining gap is minor: "avvikelse" is never defined (absolute SEK difference vs. percentage), and the relation to get_deviations_vs_last_year is left implicit.

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 all six parameters (top, month, compare_to, from/to_account, date) are documented in the schema with their defaults. The description adds only the "konto för konto" framing and result ordering, not parameter semantics, so the baseline 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?

"Avvikelser per månad: konto för konto mot föregående månad, största förändringen först" names a specific verb/operation (account-by-account deviation), the exact comparison baseline (previous month), and the result ordering. This is clearly distinguishable from the sibling get_deviations_vs_last_year without opening either schema.

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 embedded example question ("Vilka konton sticker ut den här månaden jämfört med förra?") gives an explicit usage cue, so an agent can match a user intent to this tool. It stops short of naming the sibling alternative (get_deviations_vs_last_year) or stating when-not-to-use, so it does not reach 5.

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