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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so safety is covered. The description adds genuinely non-obvious context: the source is open AIS from Digitraffic limited to the northern Baltic, and `live` only works 'when in range' — a real coverage constraint an agent must know before trusting an empty result. It omits failure behavior when an identifier is unknown or out of range, keeping it short of a 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?

Front-loads the lookup capability and identifier formats, then the answer shapes, then provenance; nearly every clause carries information. The bracketed '[NicheDB]' prefix and the trailing docs URL are low-value overhead, and the first sentence is dense enough to need a second read.

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, so the description carries the burden of describing returns, and it does so by naming the three response shapes and the fields each contains (name, type, flag, size, call sign, destination, position, speed, course, status). Only error/empty-result semantics are unaddressed, which is minor for a read-only lookup.

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% with a single parameter, so the baseline is 3, and the description earns above that by disambiguating the accepted formats — 9-digit MMSI, 7-digit IMO, or a name — which the schema only illustrates with one example value. It does not say how ambiguous names are resolved or whether alternate identifier types can be mixed.

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 and resource ('A ship or boat by MMSI... IMO number... or name'), enumerates the accepted identifier formats with digit counts, and names the upstream data source (open AIS, Digitraffic, northern Baltic). An agent can immediately tell this apart from nichedb_airplane_lookup or nichedb_train_lookup by the resource and identifiers alone.

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?

Explains what each query mode answers — `record` for static particulars, `live` for current position/speed/course when in range, `matches` when a name is supplied — which tells the agent which input form to use for which need. It stops short of explicit when-not-to-use guidance or naming a sibling alternative (e.g. a general search tool), so it is clear context without exclusions.

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