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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false; the description reinforces this by saying the tool 'opens nothing by itself', which explains why a tool named 'create_invoice' is marked read-only. It also adds the return shape (screens, buttons, fields) and a note on Fortnox API scopes/licensing, going meaningfully beyond the structured fields.

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 core behavior and the browser-tool handoff are front-loaded and well placed, but the trailing paragraph about Fortnox's official REST API, scopes and licensing reads like a tangential FAQ answer and does not help the agent decide or act. The single run-on sentence structure also makes the key 'opens nothing by itself' clause easy to miss.

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 parameters and no output schema, the description carries the burden well: it says what comes back (step-by-step screens, buttons, fields) and what to do next. The main remaining gap is that it never addresses the consequence of zero inputs — that the guidance cannot be specific to a particular invoice or customer.

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?

There are zero parameters, so the baseline is 4; the schema is empty and nothing in the description needs to compensate. It could have noted that with no inputs the returned steps are necessarily generic, but that is a minor omission.

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 states a specific resource (invoice in the user's own Fortnox account) and then clarifies the actual behavior: it returns step-by-step Fortnox instructions rather than performing the creation. That clarification is essential and disambiguates it from siblings like fortnox_send_invoice, though the name/description tension ('create' vs 'returns how to do it') costs a point.

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 explicitly gives the usage pattern: this tool 'opens nothing by itself', and the actual work is then done 'with the cotlet_browser_* tools in the user's Fortnox Cloud Browser', which is a concrete handoff to named alternatives. It stops short of stating when not to use it or when the official REST API path would be preferable, so it is clear context without explicit exclusions.

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