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

Annotations already declare readOnlyHint/ idempotentHint true and destructiveHint false, and the description reinforces rather than contradicts them by saying the tool opens nothing by itself. It adds genuine context beyond the annotations: the return is procedural guidance (screens, buttons, fields) and the actual mutation must happen through the browser tools. It does not cover failure modes, e.g. what it returns if the user is not logged in or the plan lacks the feature.

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?

Three sentences, no filler, and the essential correction ('opens nothing by itself') lands early. The final API sentence is long for a secondary justification, but it earns its place by pre-empting the 'why not just use the API' question.

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 guidance tool with safety fully covered by annotations and no output schema, the description supplies the workflow, the handoff to browser tools, and the API rationale. The remaining gap is how the specific request (which message, which user) maps onto a parameterless call.

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 the baseline is 4. Notably, the description does not explain how a specific message, course, or recipient is conveyed given the empty schema, which is the one semantic question a caller would have.

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 (send a message in the user's LearnWorlds account) and immediately clarifies the real behavior: it returns step-by-step instructions and "opens nothing by itself," then you act with cotlet_browser_* tools. That distinguishes it from the learnworlds_* API siblings and the cotlet_browser_* action siblings. The opening imperative 'Send message' still reads like a mutation at first glance, which slightly blurs the purpose until sentence two corrects 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?

Gives clear routing: call this first to get the click-path, then execute with cotlet_browser_* in the user's Cloud Browser. It also evaluates the obvious alternative — the official REST API v2 — and explains why it is not used (Learning Center plan requirement, need for your own code). It stops short of stating when not to use this tool or any prerequisites such as an already-open, authenticated Cloud Browser session.

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