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

The description adds valuable behavioral context beyond the annotations: it explicitly says it 'opens nothing by itself' and returns instructions, which aligns with readOnlyHint=true and reinforces that no external action occurs. The API aside about write access is tangential and does not describe this tool's behavior; it adds noise rather than clarity.

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 step-by-step nature is described efficiently upfront, but the trailing sentence about Procountor's REST API and 'checked 14 Oct 2026' is largely a distraction, and 'from ChatGPT, Claude or any AI agent' is filler. These dilute an otherwise short entry.

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 is reasonably complete: it says what is returned (step-by-step screens, buttons, fields) and how to proceed (browser tools). What's missing is how that step-by-step content is structured or how it relates to the user's actual invoice data. It's mostly adequate but has gaps around the format and limits of the guide.

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, so there is nothing for the description to compensate for. The baseline of 4 applies; the description does not need to document inputs.

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 opens with 'List unpaid invoices' but then clarifies that the tool 'Returns how to do it in Procountor step by step... and opens nothing by itself' — so it's a guide, not a listing tool. The revealed purpose is specific, but the conflict between the name and the actual behavior means an agent has to read carefully to understand what it will get back.

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 does point to a follow-up: 'then do it with the cotlet_browser_* tools in the user's Procountor Cloud Browser', which is useful routing. However, it does not say when to prefer this guide over other Procountor siblings, nor when to skip it, and it does not confirm what the intended deliverable to the user is.

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