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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses the non-obvious behavioral fact that the tool 'opens nothing by itself' and only returns screens, buttons, and fields — a critical disclosure for a zero-parameter tool that could otherwise be mistaken for an executor. It also explains why browser automation is required (no public Invoice2go API or self-serve keys), which preempts an agent trying another path.

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 critical constraint ('opens nothing by itself') is front-loaded in the second sentence, ahead of the browser-tool handoff. There is some filler — 'from ChatGPT, Claude or any AI agent' adds nothing, and the API-status sentence is wordy with a checked-date citation — but the remainder is dense with useful information.

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 guide tool with no output schema, the description adequately characterizes the return value (step-by-step screens, buttons, fields) and the follow-on workflow. It is slightly thin on prerequisites — e.g., whether the Invoice2go Cloud Browser must already be connected or the user signed in before the cotlet_browser_* tools will work.

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 no parameters, so the baseline is a 4 and there is nothing for the description to disambiguate. No false parameter hints are introduced, and the description correctly implies the call needs no arguments.

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 names a specific resource (unpaid invoices) and account scope (the user's own Invoice2go account), then clarifies the crucial twist that the tool returns step-by-step instructions rather than the invoice list itself. That correction is what keeps it from being misleading given the title/name, but the tension between the name ("list unpaid invoices") and actual behavior ("returns how to do it") means the agent must read past the title to understand the 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 explicitly routes the agent: this tool produces the how-to, then the actual work happens via the cotlet_browser_* tools in the Invoice2go Cloud Browser. That is clear when-to-use and a named alternative family. It does not distinguish itself from the sibling cotlet_app_guide, which plausibly overlaps as a guidance tool, so it stops short of a 5.

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