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

The description adds real context beyond the annotations: readOnlyHint/idempotentHint/non-destructive are already declared, but the description clarifies that the tool performs no browser action itself and that execution must be delegated to cotlet_browser_* tools. That is exactly the kind of behavioral clarification annotations cannot convey. It falls short of explaining the shape of the returned guidance or whether it varies by account/context.

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 fact – that this returns instructions, not invoice data – is not front-loaded; it arrives after a clause that suggests the tool does the listing. The sentence is overstuffed, bundling audience ('ChatGPT, Claude or any AI agent'), return content, non-action guarantee, delegation target, and an API-availability note. The trailing 'iFirma's official API: Yes.' is an unexplained fragment that adds no actionable value.

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, read-only guide tool the description covers the essentials: what it returns and which tools execute the steps. However, with no output schema, the agent gets no indication of the structure or length of the returned guidance, nor when this guide should be preferred over cotlet_app_guide. Adequate but with clear gaps.

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 zero parameters, so the baseline is 4. The description does not need to explain inputs, and the empty schema with additionalProperties false is self-consistent with the described zero-input, guide-only behavior.

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 'List unpaid invoices in iFirma', but the description's actual claim is that it returns step-by-step instructions rather than the invoice data itself. That is a genuinely important distinction, yet it's buried mid-sentence and the opening clause ('List unpaid invoices in the user's own iFirma account') reads as if the tool performs the listing. The core purpose – delivering a how-to guide for a browser session – is stated but not front-loaded, so an agent skimming it could mis-select.

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 clearly routes the agent: use this to learn the steps, then do it with the cotlet_browser_* tools in the user's iFirma Cloud Browser. It also explicitly states it opens nothing by itself, which prevents the agent from expecting side effects. It does not distinguish this from siblings like cotlet_app_guide, which may offer overlapping guidance.

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