Skip to main content
Glama
Sign In

ocean-schedules

by io.github.lxxmng
OverviewDiscussionsAdmin

find_best_sailings

Decision query: the best upcoming sailings on a lane, ONE per carrier (next bookable departure), ranked. Filter by date window, max transit days, min on-time reliability, cut-off still open, and direct-vs-transshipment. Use this to answer "what should I book?". etd, eta, cutoff.at and the from/to window are port-local times with no timezone offset (2026-10-01T13:00:00): quote the digits, do not convert; only retrieved_at is UTC. With Navo Tokens this costs 80 tokens for a new port pair and 10 for a repeat of the same pair within 24 hours (shared with the other lane search); an empty answer is free.

Input Schema

NameRequiredDescriptionDefault
toNoLatest departure date YYYY-MM-DD (default: +60 days)
fromNoEarliest departure date YYYY-MM-DD (default: today)
sortNoRanking (default recommended = reliability blended with transit)
cutoffNoOnly sailings whose booking cut-off has not passed. Sailings where no cut-off is held are kept by default; each option carries cutoff_status saying which case it is.
originYesOrigin port UN/LOCODE or name resolves upstream, e.g. CNSHA
destinationYesDestination port UN/LOCODE, e.g. NLRTM
transshipmentNotrue keeps only sailings that change ship, false only sailings proven direct. Omit it for both: a sailing whose routing we do not hold is returned by neither side, because we will not call a sailing direct without evidence.
max_transit_daysNoMaximum transit time in days
reliability_floorNoMinimum 90-day on-time %, 0-100
cutoff_include_unknownNoDefault true. false narrows to sailings where a deadline is actually held and still ahead.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / cutoff
      Added value: +{
+  "const": "open",
+  "description": "Only sailings whose booking cut-off has not passed. Sailings where no cut-off is held are kept by default; each option carries cutoff_status saying which case it is.",
+  "type": "string"
+}
    • addedInput schema / properties / cutoff_include_unknown
      Added value: +{
+  "description": "Default true. false narrows to sailings where a deadline is actually held and still ahead.",
+  "type": "boolean"
+}
    • removedInput schema / properties / cutoff_open
      Removed value: -{
-  "description": "Only sailings whose booking cut-off has not passed",
-  "type": "boolean"
-}
    • removedInput schema / properties / direct_only
      Removed value: -{
-  "description": "Exclude transshipment routings",
-  "type": "boolean"
-}
    • addedInput schema / properties / transshipment
      Added value: +{
+  "description": "true keeps only sailings that change ship, false only sailings proven direct. Omit it for both: a sailing whose routing we do not hold is returned by neither side, because we will not call a sailing direct without evidence.",
+  "type": "boolean"
+}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses Navo Token costs, that an empty answer is free, timezone handling, ranking behavior, and the evidence rule for direct sailings. It also explains that each option carries cutoff_status, which is important behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the decision-query purpose and filter list, then adds timezone and cost caveats that materially affect correct use. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 10 parameters and no output schema, the description provides enough behavioral context to call the tool correctly, including ranking, one-per-carrier semantics, timezone handling, and cost. It could say more about the full response shape, but the critical invocation details are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema by clarifying that from/to and related time fields are port-local with no timezone offset and should be quoted without conversion.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it finds the best upcoming sailings on a lane, one per carrier, ranked. It clearly distinguishes this decision query from raw schedule listing by framing it as answering 'what should I book?'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to use this tool to answer 'what should I book?' and lists the relevant filters. It does not name alternative sibling tools such as get_schedules or compare_lanes, so the when-not-to-use guidance is only implied.

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

All ocean-schedules toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources