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

Annotations already establish readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds real value beyond them by stating it 'opens nothing by itself' and returns screen/button/field steps, which tells the agent this is an instruction-generator, not an executor. It says little about how long or structured the returned steps are, but that is a minor gap.

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 key scoping line and the 'opens nothing by itself' clarification are front-loaded and earn their place. The final sentence about ConnectWise's REST API and the absence of a documented MCP server is background trivia that doesn't help an agent decide or invoke, so the definition is slightly padded.

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 no output schema, the description covers what is returned (step-by-step screens, buttons, fields), that nothing is mutated, and what to do next (cotlet_browser_* tools). It leaves minor gaps: no indication of ConnectWise UI version assumptions or what the agent should do if it already has a browser session open.

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 schema carries no semantics to supplement and the description has nothing to compensate for. Per the scoring rule, a parameterless tool starts at baseline 4.

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 names a specific verb and resource ('Add ticket note') and scopes it to 'the user's own ConnectWise account', distinguishing it from siblings such as connectwise_create_ticket and connectwise_read_ticket_notes. However, it also says the tool 'Returns how to do it ... step by step' and 'opens nothing by itself', so the true purpose is guidance rather than performing the add — the name and title imply a mutation that doesn't happen.

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 clear when-to-use direction: call this to get step-by-step instructions, then carry them out with cotlet_browser_* tools in the Cloud Browser. That names the follow-on path explicitly. It doesn't say when not to use it — e.g., when direct API-style sibling tools or connectwise_create_ticket would be preferable — so the exclusion side is missing.

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