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 an authorization requirement ('Kräver behörigheten view'), which is genuine behavioral context not present in the annotations.

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?

Three compact, front-loaded sentences with the core purpose stated first. The trailing 'Argument: orgnr' is mildly redundant given the schema but costs little.

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?

For a simple single-parameter read tool with safety annotations already covering behavior and no output schema to document, the description is largely sufficient. Return shape (what a draft looks like) is the only notable omission, and that is minor for a list endpoint.

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 orgnr property already documents format and how to obtain it via list_companies. The description's 'Argument: orgnr' merely restates the parameter name and adds no syntax or format detail, 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 and resource: listing pending voucher drafts that have not yet been approved or rejected. The 'pending/unapproved' qualifier distinguishes it in scope from list_vouchers, but it does not explicitly name any sibling (e.g. list_vouchers, approve_voucher_draft) to route the agent.

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?

It gives the scope condition (only drafts not yet approved or rejected) and the required 'view' permission, which is useful context. However, it offers no explicit alternatives or when-not guidance, so the agent must infer why it should pick this over list_vouchers or the approve/reject sibling tools.

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