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 real behavioral context on top of that: which documents qualify (uploaded or triaged from the inbox), their lifecycle state (not yet registered as an invoice), and the 'Scope view' note. It does not go into result shape, but no output schema exists and the criteria for inclusion effectively describe the payload.

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 resource and its qualifying state, then the follow-up workflow, then scope. Every clause carries information, though 'Argument: orgnr' is redundant with a 100%-documented schema field and could be dropped.

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 no output schema, the description carries the return-value burden and does so reasonably: it defines the returned set by classification and lifecycle state. For a single-parameter read tool with full annotation coverage, an agent has enough to call it correctly; only the concrete return fields remain unspecified.

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 schema already gives the format, an example, and points to list_companies. The description's 'Argument: orgnr' adds nothing beyond the schema, and the actual parameter meaning already comes from structured data, so this sits at the high-coverage baseline of 3.

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 specific verb+resource with scope: documents classified as supplier invoices that have NOT yet been registered. This distinguishes it from list_supplier_invoices (already registered) and from the underlying document store. It never names the closest siblings explicitly, so there is no direct differentiation for an agent scanning names alone.

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 clearly implied – find unregistered underlag so they can be registered in the ledger – and it spells out the follow-up action: create the invoice with create_supplier_invoice and link via document_id. It stops short of saying when NOT to use it (e.g. vs list_available_underlag, list_inbox, or list_documents), which is the remaining gap.

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