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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the description is consistent with them by stating the tool "opens nothing by itself." It adds genuinely useful context beyond annotations: the return shape is procedural instructions (screens, buttons, fields), which matters because there is no output schema, and it explains why browser automation is required by noting the official Mailjet MCP server is read-only.

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 is front-loaded and clear, but the opening clause "from ChatGPT, Claude or any AI agent" is promotional padding, and the closing paragraph about Mailjet's REST API and the dated official MCP server check is tangential to deciding whether to call this tool. Removing both would sharpen the definition without losing any invocation-relevant information.

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 tool with no output schema, the description covers what an agent needs: what it returns (step-by-step UI instructions), that it performs no action, and which tools execute the steps. It could be slightly more complete by indicating what the returned instructions look like structurally or whether the campaign must already exist, but the essential picture is there.

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 and the schema is trivially complete. The description correctly does not invent parameters or imply any input is needed, which is the right behavior for a no-argument guidance 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 description states a specific verb and resource ("Duplicate campaign") and then immediately clarifies the tool's real nature: it "Returns how to do it in Mailjet step by step (screens, buttons, fields) and opens nothing by itself." That distinction separates it from sibling artifacts like mailjet_update_campaign_subject or mailjet_send_campaign, which act through the API rather than returning instructions. The only drag is the opening framing, which momentarily reads as if the tool itself performs the duplication.

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?

Explicit workflow guidance is present: use this tool first, then carry out the steps with the cotlet_browser_* tools in the user's Mailjet Cloud Browser. That routes the agent to concrete sibling names. What's missing is an explicit when-not condition, e.g. what to do if the official API or another Mailjet tool could accomplish the task instead.

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