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

Annotations already establish readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds real behavior beyond that: the call validates the cart and reports which lines open, which would be left out and why, and the totals. It also discloses the downstream flow (guest pays by card, booking confirmed at payment), which tells the agent the link itself is not the booking.

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?

Four sentences, front-loaded with what the tool produces, then its validation output, the guest flow, and finally the critical charter carve-out. Every sentence carries information; the only slack is the full domain name, which is arguably needed to identify the generated link.

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 an output schema present, return details need not be spelled out, yet the description still summarizes what the check yields. Annotations cover the safety profile, and the description supplies the two things structured data cannot: the guest hand-off flow and the charter exclusion. Nothing an agent needs before calling is missing.

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 reported schema description coverage for the top-level parameter is 0%, and the description only refers obliquely to 'the chosen lines' without describing the line object or the required productId/startDate/endDate trio. The nested item schema does document fields like guests, quantity, endTime and boatLengthFt, which mitigates the gap, and the description adds the useful semantic that some submitted lines may be dropped. That is enough to clear the floor but does not compensate for the reported 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?

The description names a specific verb and artifact ('Builds the one link that puts the chosen lines in the guest's cart on experiencebamfield.com') and states the tool also validates the result. The deliverable ('Give the guest the url') is unambiguous and clearly distinct from quote/price siblings. It does not, however, name any sibling tool it should be chosen over.

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 gives a clear usage context (hand the url to the guest, who reviews and pays by card) and a genuine exclusion: a fishing charter is not carried by the link and is added from its own page. It stops short of naming an alternative tool for that case (e.g. quote_trip or get_trip_summary), so the routing is not fully closed.

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