Published forward sailing schedules on an origin→destination lane: carrier, vessel, voyage, ETD/ETA and cut-offs, soonest first. Sourced from carrier connectors (and aggregator coverage). Use this to find concrete upcoming departures to book.
| Name | Required | Description | Default |
|---|---|---|---|
| origin | Yes | Origin port UN/LOCODE, e.g. CNSHA | |
| destination | Yes | Destination port UN/LOCODE, e.g. NLRTM |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It mentions sourcing from carrier connectors/aggregators but omits critical details like whether the tool is read-only, authentication requirements, rate limits, or data latency. This leaves the agent with insufficient understanding of side effects or constraints.
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 description is extremely concise, consisting of two sentences that convey the core purpose and usage without unnecessary words. The most important information (what the tool returns and its ordering) is front-loaded.
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 a simple tool with two required parameters and no output schema, the description adequately conveys the return fields (carrier, vessel, voyage, ETD/ETA, cut-offs) and ordering. However, it could be slightly more complete by explicitly stating that the output is a list of schedules, which is currently implied.
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 input schema covers 100% of parameters with clear descriptions (UN/LOCODE strings). The description adds the concept of an 'origin→destination lane' but does not provide additional semantic detail beyond the schema's explanations. Hence, the description adds minimal value over the schema.
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 clearly defines the tool's purpose: retrieving published forward sailing schedules for a given origin-destination lane. It specifies the key data fields (carrier, vessel, voyage, ETD/ETA, cut-offs) and ordering ('soonest first'), making it distinct from sibling tools like 'find_sailings'.
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 statement 'Use this to find concrete upcoming departures to book' provides direct guidance on when to use the tool. However, it does not explicitly mention when not to use it or provide comparisons with sibling tools like 'find_best_sailings', which could lead to selection ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct aspect of ocean shipping: storms, carrier performance, lane schedules, port conditions, and alerts. Even overlapping areas like carrier reliability and lane comparisons are clearly differentiated by scope and purpose.
All tools use consistent snake_case naming. Most follow a verb_noun or noun_noun pattern, though some start with verbs (e.g., compare_lanes, find_sailings) and others with nouns (e.g., carrier_league, port_congestion). This is predictable but not perfectly uniform.
With 12 tools, the server is well-scoped for the domain of ocean scheduling. Each tool provides meaningful functionality without redundancy, covering storms, carriers, lanes, ports, and alerts.
The tool surface covers core information needs: storms, carrier reliability, lane schedules, port congestion, transit times, and alerts. Minor gaps exist, such as lacking detailed vessel info or carrier-specific data beyond reliability, but the overall coverage is strong for an informational service.
