propose_booking

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

Beyond annotations, the description discloses that no data is transmitted until apply_plan, which is a meaningful behavioral trait for a tool whose readOnlyHint is false. It also clarifies a hidden source of input (operator's config). This adds useful context about side effects and data ownership.

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 short sentences, both carrying essential meaning. The main behavior is front-loaded, and the second sentence adds a critical constraint without any waste.

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 the output schema exists and siblings show the surrounding workflow, the description is mostly complete. It covers the staging behavior and config-sourced party details, though it could have briefly mentioned that the prepared request is later listed via list_plans or applied via apply_plan. This is a minor gap.

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 description coverage is 67%, and the schema itself documents most parameters well (origin/destination as UN/LOCODEs, routing_reference from find_sailings). The description adds no per-parameter detail and leaves special_instructions unexplained, but it does provide a relevant global constraint about party details.

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 states a specific verb and resource: 'Prepare a new booking request.' It clearly distinguishes itself from apply_plan by noting that nothing is sent until apply_plan, and from propose_change/propose_cancellation by focusing on a new booking.

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?

The description gives clear usage context: use this to prepare a request, then use apply_plan to send it. It also gives an explicit exclusion—party details come from the operator's config, not from the agent. It does not enumerate alternatives, but the staging/commit flow is clear enough.

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