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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false; the description adds the meaningful behavioral detail that it 'opens nothing by itself' and only returns screen/button/field instructions, which explains why a 'create' tool is read-only. The remaining API-availability sentence is unrelated to this tool's runtime behavior, so it adds no transparency value.

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 functional core is front-loaded and clear, but two clauses waste space: 'from ChatGPT, Claude or any AI agent' is filler, and the trailing sentence about Holded's REST API and paid plans is off-topic for invoking this tool, complete with an odd future-checked date.

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 the essentials: it says what comes back (step-by-step screens, buttons, fields) and how to act on it. The gap is that it never says how the invoice specifics are conveyed with an empty input schema, which could leave an agent unsure how to call it meaningfully.

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 and the schema coverage is 100%, so the baseline is 4. The description adds nothing about inputs, which is acceptable here, though it leaves unstated how the agent should communicate which invoice to create given the empty schema.

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 states a specific resource (invoice in the user's Holded account) and, crucially, clarifies what the tool actually produces: step-by-step instructions rather than a created invoice. That distinction resolves the tension with the name 'create_invoice'. It does not, however, contrast itself with siblings such as holded_create_expense, so an agent must infer the parallel structure.

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 clear operational context: use this to get the steps, then execute them with cotlet_browser_* tools in the Holded Cloud Browser. What is missing is any when-not guidance or explicit routing to alternatives (e.g. cotlet_app_guide, holded_create_expense) for agents that have a different goal.

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