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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces rather than repeats them by explaining the surprising part: the tool returns a guide and performs no action. That is genuinely valuable context an agent would otherwise misread from the mutation-flavored name. It does not describe response length or detail level beyond 'step by step', keeping it below 5.

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, all carrying load: what is returned, that it performs nothing, the follow-up tools, and the API-absence rationale for why browser automation is needed. The enumeration 'from ChatGPT, Claude or any AI agent' is filler that could be dropped, and the leading 'Add client' phrasing is slightly misleading before the correction lands.

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, no-output-schema tool, the description covers what it returns, what it does not do, and the precise next tool family to use. The lack of a public FitSW API is stated with a check date, which explains why this and the browser tools exist at all. Only the granularity/format of the returned steps is left unspecified.

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 disambiguate; baseline is 4. The absence of arguments is consistent with a static procedure-lookup tool, and nothing in the description implies hidden inputs.

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 outcome — it returns FitSW add-client instructions (screens, buttons, fields) rather than performing the action, and explicitly says it 'opens nothing by itself'. The opening phrase 'Add client in the user's own FitSW account' momentarily implies a mutation, but the following clause corrects it, and the tool is clearly distinguishable from the fitsw_* siblings and the cotlet_browser_* tools.

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?

Usage is explicit: call this to learn the FitSW procedure, then 'do it with the cotlet_browser_* tools in the user's FitSW Cloud Browser'. The named alternative and the workflow order are both given, so an agent knows the next step. It stops short of saying when NOT to use it (e.g. if the user only wants to read client data, fitsw_list_clients applies), so it is not a full 5.

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