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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so safety is covered. The description does add real value beyond them: the notion of 'verified' MMSIs, the freshness taxonomy behind the status filter, and the caveat that older positions are last known observations rather than current locations. It stops short of saying how results are ordered, truncated, or how 'latest actual' is determined.

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?

Three short sentences, front-loaded with what is returned, then filtering, then the key interpretation caveat. No filler or repetition of schema/annotation content.

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 two-parameter, non-destructive list tool with no output schema and full annotation coverage, this is nearly enough: it states what comes back and warns about stale data. The remaining gap is the undocumented 'status' enum values and result ordering/limits, which are left unresolved.

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 50% — 'ship' is documented in the schema, while 'status' only has bare enum values. The description partially compensates by mapping coverage language ('fresh, stale or missing') onto the status filter, but it never explicitly reconciles those words with the enum values 'current', 'stale', 'unmapped', 'awaiting_report', leaving that mapping to inference.

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?

Specific verb ('Read') plus concrete resources: verified catalog ship MMSIs, latest actual AIS positions, and coverage freshness. It is distinguishable from catalog siblings like list_cruise_ships by the AIS/coverage focus, though it never names get_ship_positions, the closest-looking sibling, so an agent must infer the split.

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 implied by the filter dimensions ('Filter by ship UUID/slug or coverage status'), so an agent can see the intended access pattern. However, there is no explicit when-to-use/when-not guidance and no named alternative (e.g., get_ship_positions) to route between.

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