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), so the description's job is to add beyond that. It does: it states the result is computed server-side from live Fortnox data over all pages, telling the agent data is fresh and complete rather than paginated. It says nothing about output shape, but an output schema exists.

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?

The detection rules are front-loaded, followed by an example question, then provenance. Dense but efficient. The Fortnox API URL is mild boilerplate, though it usefully signals the data source.

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 annotations covering safety, an output schema covering returns, and a fully-described schema, the description only needs purpose, trigger and data scope — all present. Minor gaps remain around what counts as 'before payment' beyond the fram default, but nothing essential to invoking it is missing.

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 the three parameters (fram, dagar, stort_belopp) are already fully documented, including defaults and caps. The description conceptually maps to them (changed shortly before payment, large invoices) but adds no syntax or tuning guidance beyond the schema, making the baseline 3 appropriate.

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 names three concrete detection rules (suppliers changed shortly before a payment, underlag whose bankgiro differs from the register, new suppliers with large invoices), which is a specific verb-plus-resource statement rather than a restatement of the title 'Betaluppgifter'. This makes it clearly distinguishable from sibling tools like find_duplicate_supplier_invoices or get_payment_list.

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 ('Har någon leverantör bytt bankgiro? ... innan vi betalar?') supplies a clear triggering scenario: a pre-payment control check. It stops short of explicit exclusions or naming which sibling to use instead (e.g. get_payment_list for the actual payment run), so it is clear context without routing rules.

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