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

Contributes real behavior beyond annotations: 'opens nothing by itself' clarifies the tool is non-executing despite the action-oriented name, and the step-by-step return format (screens, buttons, fields) is disclosed. The annotations (readOnlyHint=true, openWorldHint=false, idempotentHint=true, destructiveHint=false) are consistent with that. The trailing note about Mautic's API and lack of an official MCP server adds provenance context but is somewhat tangential.

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 routing message is front-loaded, but the final sentence about Mautic's API and checking for an MCP server on 23 Oct 2026 is a dated aside that doesn't help the agent call the tool. The three-clause middle sentence ('Returns how to do it... opens nothing... then do it with') is dense but does carry necessary distinctions.

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 supplies the essential contract: what is returned (step-by-step UI instructions), what is not done (nothing opens), and the follow-up tool family. An agent has enough to invoke and act. It lacks only guidance on what input context (e.g., contact identity or segment name) to have ready beforehand.

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?

Zero parameters, so the baseline is 4. The description correctly carries the burden by explaining that the target account is the user's own Mautic account rather than a parameter, and that the specific segment/contact selection happens in the browser flow, not here.

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?

States a specific verb and resource ('Change contact segments in the user's own Mautic account') and names the account scope. It is reasonably distinguishable from siblings like mautic_create_segment, though it doesn't explicitly contrast with them. The mixed framing as a guidance tool rather than an executor ('Returns how to do it in Mautic step by step') muddies whether it performs the change or explains it.

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?

Explicitly routes the agent: this tool returns instructions, and the actual action is done with cotlet_browser_* tools in the Mautic Cloud Browser. That is clear sequencing guidance covering the when-to-use and the follow-up step. It doesn't state when NOT to use it (e.g., versus mautic_create_segment for new segments), leaving one gap.

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