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

Annotations already declare readOnly, non-destructive and idempotent, and the description reinforces this by stating it 'opens nothing by itself', which prevents an agent from assuming the refund happens on this call. It adds the concrete shape of the return (step-by-step screens, buttons, fields) and the required execution channel (cotlet_browser_* in the user's Cloud Browser session), which goes beyond the annotations.

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 instruction (returns steps, performs nothing, then use browser tools) is front-loaded and clear, but the marketing framing ('from ChatGPT, Claude or any AI agent') and the API/MCP-server note ('checked 23 Oct 2026') are tangential and eat space without helping the call decision.

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?

With no parameters, no output schema, and safety covered by annotations, the description supplies the one thing that matters: what comes back (ordered UI steps) and what the agent must do next. It stops short of noting any prerequisites (login state, ticket eligibility) or the format of the returned steps.

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 and the schema is fully described, so the baseline applies. The description correctly implies it is an unparameterized guidance lookup with no ticket identifiers or amounts to supply; nothing about parameters is misrepresented.

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 (refund tickets in the user's Billetto account) and clarifies that the tool only returns step-by-step instructions rather than performing the refund, which disambiguates the name. It does not distinguish itself from the closely related sibling billetto_cancel_free_tickets, so an agent cannot tell from the text which of the two applies to free vs paid tickets.

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 a usable workflow: call this first to get the screens/buttons/fields, then execute with the cotlet_browser_* tools in the Cloud Browser. It offers no exclusions or alternative routing (e.g., when to prefer billetto_cancel_free_tickets, or when refunds are not possible), so the when-not guidance is missing.

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