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

The annotations already establish readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, and the description is consistent with them ('opens nothing by itself'). It adds useful confirmation that no action is performed, but the long paragraph about MYOB's official REST API, app registration, and OAuth consent describes why the tool exists rather than behavior an agent needs in order to invoke it.

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 description opens with promotional phrasing ('from ChatGPT, Claude or any AI agent') and then spends an entire sentence on MYOB's API access process, including a 'checked 14 Oct 2026' date, which does not help an agent call this tool. The genuinely useful core — that it returns step-by-step instructions and then you act via cotlet_browser_* — is buried in the middle.

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 tool with no output schema, the description does say what is returned ('steps, screens, buttons, fields') and points to the browser tools for follow-up. However, the ambiguous framing about listing invoices versus returning a guide leaves an agent uncertain whether it will receive invoice data or only instructions, which is the key completeness gap.

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 and the schema is trivially complete, so there is no parameter meaning the description must supply. The baseline for a 0-parameter tool is 4, and the description contains no misleading parameter information.

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 does disclose the actual deliverable ('Returns how to do it in MYOB step by step (screens, buttons, fields) and opens nothing by itself'), but the leading claim that it will 'List overdue invoices' describes retrieval of data, which is not what the tool does. An agent must read past the headline to learn this is a guide/instructions tool, and nothing distinguishes it from the sibling cotlet_app_guide that likely serves a similar 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?

It gives a clear workflow context: call this first, then perform the steps using the cotlet_browser_* tools in the MYOB Cloud Browser. However, it offers no explicit when-not-to-use guidance and does not say how it differs from other guide/app tools such as cotlet_app_guide or when to skip this and go straight to the browser tools.

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