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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: results are 'computed on the server from live Fortnox data' and span 'all pages', disclosing data freshness and pagination behavior.

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 scope and status list come first, followed by illustrative questions and a short provenance note; each part adds something. Mild redundancy with the title and the schema's status list keeps it from a 5.

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 not be explained, and annotations cover safety. The description completes the picture with source, freshness and full-pagination behavior; only the sibling disambiguation gap remains.

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 (status, fromdate, todate, leverantor) are already documented, including defaults. The description's mention of statuses and amounts/due date largely restates what the schema provides, so 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 (retrieve supplier invoices) and enumerates the status buckets it covers, which makes it clearly distinct from find_customer_invoices. It does not differentiate itself from the very close sibling list_supplier_invoices, leaving an agent to guess between the two.

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?

Two example questions ('which invoices from Telia this year?', 'which supplier invoices await attest?') implicitly illustrate when to reach for it, and the status enumeration implies the filtering modes. There is no explicit guidance on when NOT to use it and no named alternative for plain listing (list_supplier_invoices).

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