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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds the useful non-obvious behavior that it performs no action and merely returns instructions, but says nothing about the size, format, or reliability of those instructions or the API-availability note's practical implications.

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 purpose is front-loaded in the first sentence, but the second sentence runs long and buries the key behavior ('opens nothing by itself') mid-clause. The closing sentence about Mautic's official API is tangential trivia that doesn't help an agent decide whether or how to call the tool.

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 no-parameter instruction-returning tool, the description covers the essential workflow: get steps here, then execute them with the browser tools. It could be stronger by describing what the returned steps look like or noting that the returned guidance may be generic rather than account-specific, but nothing critical to correct invocation is missing.

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 nothing for the description to clarify; baseline for a parameterless tool would normally be 4. However, the description's emphasis on 'email stats' could mislead an agent into thinking it needs to supply an email ID or campaign context, which the empty schema does not accept – a small but real ambiguity in meaning.

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 says it returns step-by-step instructions for finding email stats in Mautic (screens, buttons, fields), which is a specific outcome, but it never states plainly whether any actual stats data is returned. A reader must infer from 'opens nothing by itself' and 'do it with the cotlet_browser_* tools' that this is a how-to guide, not a data-fetching tool – an inference that takes effort and could easily be wrong.

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 clearly states the follow-up path: use cotlet_browser_* in the user's Mautic Cloud Browser after getting the steps, and notes that it opens nothing itself. It doesn't say when to skip this tool (e.g., if you already know Mautic's UI) or mention any alternative like cotlet_app_guide, so the routing guidance is helpful but incomplete.

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