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

Annotations already declare readOnlyHint/idempotentHint true and destructiveHint false, so the safety profile is covered. The description adds genuinely new behavior: it performs no action itself, returns procedural content (screens, buttons, fields), and requires a Fortnox Cloud Browser session to actually complete the task — plus scope/licence constraints on Fortnox's API. The API paragraph is somewhat tangential but does explain why a guided-browser flow is used instead of the REST API.

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 operational content is front-loaded and reasonably tight, but the closing paragraph about Fortnox's public API, scopes, integration registration and licensing dates ('checked 14 Oct 2026') is three clauses of background that dilutes the actionable instruction. A direct statement of what the tool returns would be a better use of that space.

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 zero-parameter tool with no output schema and full annotation coverage, the description covers the essentials: what it returns (step-by-step guidance), that it is non-acting, and what to call next. The remaining gap is that it never clearly resolves the 'list invoices' framing against the guidance-only return, which is the one thing an agent most needs settled.

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?

The tool takes no parameters, so there is no parameter meaning to add; the baseline of 4 applies. The description does not invent or misdescribe any inputs.

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 name and opening sentence promise 'List unpaid invoices', but the second sentence reveals the tool actually returns a step-by-step how-to and 'opens nothing by itself' — the invoices are never returned. That self-correction keeps it from being flatly misleading, but an agent reading only the first line would form the wrong expectation about the return value.

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?

The description gives a clear workflow: get the guide here, 'then do it with the cotlet_browser_* tools in the user's Fortnox Cloud Browser'. That is useful routing to a concrete alternative, but there is no statement of when NOT to use this tool, when the same goal is better served by a sibling (e.g. cotlet_app_guide), or what prerequisites the browser session needs.

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