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

Annotations declare readOnlyHint=true, which is surprising for a tool named 'create_invoice', and the description explicitly reconciles it: 'opens nothing by itself'. That is exactly the kind of context annotations cannot convey on their own. It also discloses the return shape at a high level and the plan-tier limitation, though it omits whether a browser session must already be open before the follow-up calls succeed.

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 fact, that this returns steps and performs nothing, is front-loaded, which is good. But the prose is a semicolon-chained run-on and the trailing API/pricing aside with a 'checked 14 Oct 2026' date adds little for an agent deciding whether to call it.

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, no output schema, and a simple read-only behavior, the description covers what an agent needs: what is returned, that nothing is mutated, and which tools to chain next. Only prerequisites for the follow-up browser calls are left implicit.

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 the baseline is 4 and there is nothing for the description to disambiguate. The description correctly implies no inputs are needed by describing the response as generic guidance rather than account-specific output.

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 makes clear this tool does not create anything: it 'Returns how to do it in Odoo step by step (screens, buttons, fields) and opens nothing by itself', then hands off to the cotlet_browser_* tools. That resolves the tension with the name 'create_invoice' and tells an agent exactly what it gets back. It stops short of naming a sibling guide tool it might be confused with, but the verb/resource is unambiguous once read.

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 gives an explicit workflow: call this first to get the steps, then execute them with cotlet_browser_* in the user's Odoo Cloud Browser. It also justifies why the browser path is required (Odoo's external API is unavailable on One App Free/Standard plans). There is no explicit statement of when NOT to use it, e.g. for accounts on Custom plans where an API path might exist.

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