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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds the key behavioral fact: the output is a proposal requiring approval rather than a posted voucher. It also discloses provenance ('computed on the server from live Fortnox data... over all pages'), telling the agent results are live and paginated. No rate limit or failure-mode detail is given.

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?

Front-loaded with the purpose, followed by the example and then a short provenance note; each segment serves a function. Slightly dense with mixed-language fragments, but no filler sentences.

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 shape need not be restated. Together the description, full schema coverage, and annotations give an agent enough to call it correctly: scope, that the result is a proposal, and that data is live. Only the sibling routing (supplier invoices vs receipts) remains 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 four parameters (max, filer, kontering, betalt_med) already carry their own descriptions including defaults and allowed values. The prose adds no parameter-specific detail beyond the example implying betalt_med=kort, 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?

States a specific verb+resource: receipts and expenses in the inbox folder 'Kvitto & Utlägg' are interpreted and coded into verifikat, delivered as a proposal to approve in one sweep. The scope ('i inkorgens mapp Kvitto & Utlägg') distinguishes it from prepare_inbox_supplier_invoices without naming it. The one ambiguity is that the leading 'Bokför kvittona' sounds like a write, though the body corrects this to a proposal.

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?

Provides a concrete example question ('Bokför kvittona som ligger i inkorgen. De är betalda med företagskortet.') that shows the trigger context and how the payment method parameter is expressed. However it does not explicitly exclude alternatives such as prepare_inbox_supplier_invoices or state prerequisites for the inbox folder being populated.

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