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

The description does add behavior beyond the annotations by clarifying that nothing is opened and the tool only emits instructions, consistent with readOnlyHint=true and openWorldHint=false. It stops short of saying what the returned guidance actually contains beyond generic 'screens, buttons, fields'. The trailing paragraph about Invoice Ninja's REST API is irrelevant to this tool's behavior and dilutes the useful disclosure.

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 message ('returns steps, opens nothing, then use cotlet_browser_*') is buried in the middle of the sentence, and the closing API-availability paragraph with a 'checked 14 Oct 2026' date serves no purpose for invoking this tool. The size is not justified by the information delivered, and the front-loading is weak because the actual purpose appears after the agent-facing preamble.

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 and no output schema, the description carries the full burden of explaining the return, and it only gestures at 'step by step (screens, buttons, fields)'. For a tool whose whole value is the guidance it emits, a sentence on the shape or scope of that guidance (e.g. which overdue-invoice screens it covers) would materially help. It is adequate but thin for a zero-annotation-surface tool.

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 there is no parameter meaning to convey; the schema is empty and fully consistent with an unfiltered listing/guide. Baseline 4 applies for a no-parameter tool.

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 promise 'list overdue invoices', but the description redefines the tool as something that 'Returns how to do it in Invoice Ninja step by step (screens, buttons, fields)'. An agent cannot tell from this whether it gets invoice data or a how-to guide, which is the single most important fact about the tool. It does at least distinguish itself from the cotlet_browser_* family by saying those tools perform the 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 sequencing is stated explicitly: this tool 'opens nothing by itself; then do it with the cotlet_browser_* tools in the user's Invoice Ninja Cloud Browser'. That is real workflow guidance. However, there is no comparison to the closely-related cotlet_app_guide or cotlet_apps siblings, and no statement of when this tool is preferable to just navigating Invoice Ninja directly.

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