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

Annotations already declare readOnlyHint=true, idempotent and non-destructive; the description reinforces this by stating the tool 'opens nothing by itself', which explains why a booking tool is read-only. It also discloses the return shape (step-by-step screens, buttons, fields) and the handoff requirement to a Cloud Browser session. The API paragraph (keys only by email to api@virtuagym.com) is useful background for why automation is browser-based, though it sits slightly outside the call's behavior.

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?

Front-loaded with the action, then the return value, then the constraint ('opens nothing'), then the next step — a sensible order. The closing API paragraph, including a dated verification note, is peripheral and lengthens the definition without changing how an agent calls it.

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?

The return value is described and no output schema exists, so that side is covered. The gap is on input: with an empty schema the agent cannot tell whether it must first identify the member/class via virtuagym_list_members and virtuagym_list_classes, or whether context is inferred from the session, and the description never says. For a tool whose whole purpose is a targeted booking, that missing linkage is a meaningful omission.

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 there is no per-parameter meaning to add and the baseline applies. However, the empty schema raises an obvious question the description never answers: how the target member and class are conveyed, since neither appears as an input.

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 ('Book member into class in the user's own Virtuagym account') and immediately disambiguates the mechanism: it returns step-by-step instructions and 'opens nothing by itself', rather than performing the booking. That distinction separates it cleanly from the virtuagym_* action siblings and from the cotlet_browser_* execution 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?

Explicitly routes the agent: call this first to get screens/buttons/fields, then execute with the cotlet_browser_* tools. That is a clear two-step workflow with a named alternative. It stops short of stating exclusions, e.g. when to use virtuagym_list_members or virtuagym_list_classes to find the member/class first, or when the browser path is unnecessary.

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