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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely non-obvious behavior: it returns a link rather than the file, and the file never flows through the conversation – a distinction an agent could not infer from the schema or 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 short sentences, front-loaded with what is returned and how it is delivered; the API path and docs link are compact supporting detail rather than filler.

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?

Output schema and annotations carry the structural load, and the description covers the one thing they cannot: that the result is a downloadable link, not file content. The remaining gap is sibling disambiguation against read_invoice_pdf.

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 coverage is 100% with a single well-described parameter, so baseline is 3. The description only restates it as '{DocumentNumber}' in the API path and adds no format, sourcing, or lookup guidance beyond the schema.

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: fetching an invoice as a PDF, and names the concrete Fortnox endpoint. However, it never distinguishes itself from the sibling read_invoice_pdf (or get_invoice), so an agent cannot tell from this text which one to pick.

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?

No explicit when-to-use guidance and no mention of alternatives, despite an obviously overlapping sibling (read_invoice_pdf). The only implicit cue is 'a link the person opens', which hints at human-facing delivery but is not framed as a selection rule.

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