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

The annotations already declare readOnlyHint=true and destructiveHint=false, and the description is consistent with them, explicitly stating it 'opens nothing by itself.' It adds real context beyond the annotations by disclosing the return shape (screens, buttons, fields) and the required follow-on browser tools. The trailing remark about sevdesk's REST API and the 'checked 14 Oct 2026' date add noise and a mild implication of API access that the description never explains.

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 guidance is front-loaded in the first two sentences, which are tight and useful. The final sentence about the official sevdesk REST API and a dated verification adds no actionable meaning for invoking this tool and dilutes the message.

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, no-output-schema tool the description covers what matters: what it returns (step-by-step UI instructions), that it performs no action, and which tools complete the job. It leaves minor gaps around prerequisites, such as whether the user's sevdesk account must already be connected before the Cloud Browser step.

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 zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The description correctly implies no arguments are needed to obtain the guide, though it could have said so outright to reassure the agent.

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 verb+resource are named (create an invoice in the user's sevdesk account) and the second sentence clarifies the actual behaviour: it returns a step-by-step guide rather than performing the action. That clarification is crucial and distinct from the browser siblings it names. It loses a point because the opening sentence reads like the tool itself creates the invoice, so the agent must reach sentence two to learn it is really a how-to tool.

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 does give a next-step routing rule (use cotlet_browser_* tools to actually perform the creation) and implicitly scopes usage to sevdesk invoicing. But it never states when NOT to use it, nor distinguishes itself from nearby siblings such as sevdesk_send_invoice, sevdesk_book_voucher, or the generic cotlet_app_guide. The guidance is implied rather than explicit.

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