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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuine context beyond them: results are computed server-side from live Fortnox data and aggregate over all pages, so the agent knows the output is fresh and complete rather than a paginated sample.

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?

It is front-loaded with the metric definition, followed by an example question and then data provenance — three compact, non-redundant sentences with nothing that repeats the schema or annotations.

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 and annotations are rich, so return values and safety need not be explained. The description covers what counts as a deviation and where the data comes from; the only omission is how the "usual" baseline is determined (methodology/threshold), which an agent might otherwise ask about.

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 the single parameter (dagar) is fully documented with default 60 and max 365 in the schema. The description adds nothing about the parameter, so the baseline 3 applies — the schema does the work.

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 gives a precise definition of the metric: new supplier invoices booked to a different account or with a different VAT rate than the supplier's usual. That is a specific resource plus a specific detection criterion, not a restatement of the name. It stops short of naming how it differs from the closest siblings (find_duplicate_supplier_invoices, get_deviations_vs_last_month).

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?

Usage is implied through an example question ("Har någon leverantörsfaktura konterats annorlunda än vanligt?"), which tells the agent the kind of user intent that should route here. There is no explicit when-not-to-use guidance and no mention of the neighbouring deviation/duplicate tools that could be confused with it.

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