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

Annotations already mark this readOnly/non-destructive, and the description is consistent with that ('stateless price preview and does not save the selection'). Beyond that it discloses real behavioral constraints: Sedna is the only source of truth for prices, never compute totals in the LLM, do not add payable_now to payable_at_base, and keep the refundable deposit separate. This is rich, non-obvious operational context.

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?

Reasonably sized and front-loaded with the core purpose and the price-authority rule. Every sentence carries an instruction the agent needs, though a couple of lines drift toward downstream output handling rather than the call itself. No filler or tautology.

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 an 11-parameter tool with no output schema, the description compensates well: it names the return fields to quote (customer_cost_summary.full_customer_cost, payable_now, payable_at_base, refundable deposit) and explains how to present them. Combined with workflow and price-authority guidance, an agent has what it needs to call and interpret this 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?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-tool provenance (id_boat/id_tbf1 come from search_boats) and semantic handling of selected_extras (send the complete list, and repeat it in booking_create). It also frames currency, ports and payment options as inputs. This meaningfully exceeds what the schema text alone conveys.

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+resource: applies customer selections and returns server-recalculated booking details, and clarifies it is a stateless price preview that does not persist. It implicitly separates itself from booking_create (the save step). It doesn't address why one would pick booking_detail_mod over the sibling booking_detail, so it stops short of full sibling differentiation.

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 clear workflow context: copy id_boat/id_tbf1 from search_boats, and if the customer proceeds, repeat the extras in booking_create. The when-not-to-use case (this preview does not save) is explicit. No guidance on choosing between booking_detail and booking_detail_mod, which are the closest siblings.

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