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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds genuinely useful behavior: results are computed server-side from live Fortnox data across all pages, so the agent knows there is no client-side pagination gap. It omits finer points such as whether unbooked invoices are included by default, which the filter schema partially covers.

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?

A single compact paragraph, front-loaded with the definition, then the example question, then the computation note. The leading 'Dubblettkontroll:' repeats the title, costing a little space, but otherwise nothing is wasted.

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, return values need no explanation, and annotations cover safety. The description supplies the matching logic, data source, and scan scope, which is what an agent needs. Only minor gaps remain, e.g. whether obokförda invoices are treated differently in duplicate detection.

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 parameters (filter, fromdate, hela_historiken) are already fully documented in the schema. The description adds no additional detail about parameter interaction or formats, so baseline 3 applies. The 'over all pages' note hints at the hela_historiken behavior but does not explain it directly.

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 precise operation and matching rule: supplier invoices sharing the same supplier+amount, or the same invoice number. This is clearly distinct from the sibling listing tools (list_supplier_invoices, find_supplier_invoices), which do not perform duplicate detection. An agent can pick this tool from the name plus definition without opening the 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 concrete example question ("Har vi registrerat någon leverantörsfaktura två gånger?") makes the intended scenario obvious. It does not name an alternative or state when not to use it, but the matching criteria define the usage well enough for correct selection.

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