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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces and extends that by stating it 'opens nothing by itself' and specifying the return content (screens, buttons, fields). It does not contradict the readOnly annotation despite the 'create' name — it clarifies the non-mutating nature. Minor gap: no mention of whether guidance is version/locale specific.

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 key caveat ('returns how to do it... opens nothing by itself') is present but buried mid-sentence after client-list filler ('from ChatGPT, Claude or any AI agent'). The trailing 'e-Boekhouden's official API: Yes' is unexplained and adds little.

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 output schema, the description carries the burden of describing returns and does so concretely (step-by-step screens, buttons, fields). What remains unclear is what invoice details the agent must supply or how the guidance is tailored, but for a zero-parameter instructional tool the coverage is reasonable.

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 (schema is an empty object with full coverage), so there is no parameter semantics to explain; baseline of 4 applies. The description adds nothing about parameter behavior, which is appropriate here.

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 title say 'Create invoice', but the description reveals the tool actually returns step-by-step instructions rather than creating anything ('opens nothing by itself'). That core purpose is only stated after a clause about which AI clients can call it, so an agent skimming the first sentence could easily misread the tool as a mutation API. The named handoff to cotlet_browser_* tools does help distinguish the follow-up action.

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: call this to get the click-by-click recipe, then execute it with the cotlet_browser_* tools in the Cloud Browser. However, it gives no guidance on when to prefer this over siblings like cotlet_app_guide or e_boekhouden_book_mutation, and no exclusions.

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