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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds a consistent plain-language confirmation ('Changes nothing and sends nothing') plus a concrete list of what comes back. Because there is no output schema, disclosing the return contents — CHF total, payment terms, pilot-price flag, form fields and choice ids — is genuinely valuable. It stops short of describing error behavior or how options affect pricing.

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?

Two sentences, front-loaded with the verb and resource, and the second sentence delivers the safety statement in four words. The first sentence is long and list-heavy but every item is a distinct return value the agent will act on, so little is wasted.

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?

Given a read-only, three-parameter tool with a nested options object and no output schema, the description covers purpose, safety, and the return payload well enough to call it confidently. Remaining gaps — what lang changes, and error cases for an invalid offer or unavailable extra — are modest for a preview tool.

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?

Coverage is low at 33%, with lang, choice, and the nested object itself undocumented in the schema, so the description has room to compensate. It does clarify conceptually that choices are 'options' and that valid choice ids come back from this same tool, which helps the callers of choice/tier/extras, but it never explains lang or the interplay of monthly/groups. Useful but partial compensation for the coverage gap.

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 ('Prices one orderable service') and couples it to the sibling it feeds ('the form fields and choice ids that request_order needs'), so the agent can separate quoting from ordering without opening a schema. The scope is a single service with its options, which is unambiguous against list_services or request_order.

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 implicitly routes the agent: call this before request_order, and it does not mutate anything, so it is safe to call repeatedly to preview a price. It names the follow-up tool explicitly, but gives no guidance on when to prefer list_services or get_free_slots, nor how to handle a failed quote.

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