Fused port-congestion signal for a port (UN/LOCODE): effective level (mild/moderate/severe), expected added wait in days (for ETA-band widening), a 0–1 confidence, and the independent readings behind it: measured vessel waiting times, port-call throughput and AIS wait/density. With Navo Tokens this costs 10 tokens per call; an empty answer is free.
| Name | Required | Description | Default |
|---|---|---|---|
| port | Yes | Port UN/LOCODE, e.g. NLRTM |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the billing model (10 tokens per call with Navo Tokens, empty answer free) and the provenance of the signal (measured vessel waiting times, port-call throughput, AIS wait/density). It does not cover data freshness/lag, error behavior for unknown LOCODEs, or any rate limits, which keeps it below 5.
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?
It is a single dense sentence, but the payload (level, wait in days, confidence, source readings) and the cost note are front-loaded and each clause carries distinct information. Slightly overstuffed with parentheticals, though nothing is redundant.
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?
No output schema exists, and the description compensates by enumerating the four return components, including units (days) and scale (0-1 confidence) — exactly what an agent needs to consume the result. Missing only operational context such as data latency and failure modes for unknown ports.
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% and the single 'port' parameter already documents the UN/LOCODE format with an example (NLRTM). The description only restates the same format, adding no validation rules, accepted casings, or behavior for unresolvable codes, so the baseline 3 applies.
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 resource ('Fused port-congestion signal for a port (UN/LOCODE)') and then enumerates what the signal returns: effective level, expected added wait in days, 0-1 confidence, and the underlying readings. Nothing in the sibling set (carrier_reliability, lane_storm_exposure, get_schedules) does port-level fused congestion, so an agent can route to it unambiguously.
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?
Usage is only implied: the parenthetical '(for ETA-band widening)' hints at one downstream use case, and the token-cost sentence signals a metered tool, but there is no explicit when-to-use/when-not or named alternative (e.g. lane-level risk tools) to compare against. An agent knows what it does but must infer when it beats the lane-oriented siblings.
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.
