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

The annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. Beyond that, the description adds real value: 'opens nothing by itself' clarifies that invoking it has no side effects and that a browser session must follow. The API-credential caveat (request form, Tenant ID, Millennium Systems outreach) further explains why the browser path is needed.

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 behavior ('returns step-by-step instructions, opens nothing, then use the cotlet_browser_* tools') is front-loaded and clear. The trailing paragraph about Meevo's Public API and a checked date is a tangent that pads the definition without helping an agent decide or invoke, and the 'from ChatGPT, Claude or any AI agent' clause is filler.

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 read-only, no-param how-to tool this is largely sufficient on behavior, but the description never clarifies what the returned instructions actually look like or that it is not returning appointment records despite its name. The API aside raises more questions than it answers and displaces information an agent would need, such as which cotlet_browser_* call to start with.

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 there is nothing for the description to disambiguate; the baseline for a no-param tool applies. The description's only parameter-adjacent content is the note that no input is taken, which is consistent with the empty schema.

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 name and title say 'list appointments,' but the description actually says it 'Returns how to do it in Meevo step by step (screens, buttons, fields)' rather than returning appointment data. That qualification saves it from being misleading, but the verb+resource framing conflicts with what the tool really does. It also never distinguishes itself from sibling meevo_book_appointment or meevo_find_client.

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 implies usage by telling the agent to 'then do it with the cotlet_browser_* tools in the user's Meevo Cloud Browser,' which is a useful follow-up path. But it never states when to choose this over a direct API approach or over sibling meevo_* tools, and there are no explicit exclusions.

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