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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the description reinforces this by explicitly stating the tool 'opens nothing by itself' and returns step-by-step instructions rather than mutating anything — this explains WHY it is read-only, which structured hints alone cannot. The final sentence about MYOB's official REST API, app registration and OAuth consent is tangential to this tool's behavior and risks distracting the agent toward a path this tool does not implement.

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 disclosure (returns a how-to, opens nothing, follow up with browser tools) is front-loaded and earns its place. The trailing sentence about MYOB's REST API, access forms, app registration and per-file OAuth consent is lengthy and not actionable for invoking this tool, bloating the definition and diluting the main message.

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 guidance tool with a fully covered schema and no output schema, the description covers the essentials: what it returns (screens, buttons, fields) and the required follow-up tooling. It does not describe the output shape in any more detail, but with no output schema that is a minor omission rather than a blocking one.

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 description makes no parameter claims, so there is nothing to misdescribe. Baseline of 4 applies for a parameterless tool, though the absence of any statement about what inputs (if any) the guidance is shaped by leaves a small gap.

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 states a concrete verb and resource and, critically, clarifies that the tool does not itself create the invoice in MYOB: it 'Returns how to do it in MYOB step by step (screens, buttons, fields) and opens nothing by itself.' That resolves the tension with the name/title, which would otherwise imply a write. It gives no differentiation from siblings such as myob_create_bill or myob_send_invoice, so it stops short of a 5.

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 does supply sequencing guidance — after getting the instructions, perform the work 'with the cotlet_browser_* tools in the user's MYOB Cloud Browser' — which is genuinely useful. However, there is no when-not-to-use guidance and no hint about how this differs from other MYOB tools in the sibling set, so the agent must infer context.

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