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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with the important behavioral fact that the tool opens nothing and only returns textual instructions. That is genuine value beyond the annotations: an agent knows the actual state change must come from the cotlet_browser_* family.

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 purpose is front-loaded, but the third sentence about Invoice Ninja's REST API, complete with a 'checked 14 Oct 2026' date, is irrelevant to selecting or invoking this tool and pads the definition. 'from ChatGPT, Claude or any AI agent' is similarly expendable.

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 instructional tool with no output schema, the description covers what it returns and what the agent must do next, which is the critical information. It leaves minor uncertainty about the scope of guidance offered versus cotlet_app_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 zero parameters, so there is no parameter semantics to explain; baseline 4 applies. The description correctly implies a parameterless call by describing an answer-only 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 second sentence states the actual deliverable precisely: step-by-step instructions with screens, buttons and fields, and explicitly says it opens nothing itself. This resolves the misleading 'record payment' name, which sounds like a mutation. It does not, however, distinguish itself from cotlet_app_guide, which appears to serve a similar instructional role.

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 names the follow-up path clearly ('then do it with the cotlet_browser_* tools in the user's Invoice Ninja Cloud Browser'), which tells the agent this tool is a prerequisite step. It gives no guidance on when to prefer it over cotlet_app_guide or how it relates to invoice_ninja_create_invoice / send_invoice.

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