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

Beyond readOnly/idempotent/openWorld annotations, it discloses ordering (newest first), positional semantics (last known position), a source-attribution caveat ('from a source we may pass on'), the meaning of 'truncated', per-call credit cost, plan-tier box limits, and free-tier freshness/credit throttling. These are behavior-shaping facts an agent cannot get from the annotations or schema.

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 core operation and ordering come first, and every clause carries a fact (limits, costs, truncation, freshness). It is dense and semicolon-chained, blending plan limits into the same paragraph as return semantics, which costs some readability but not information.

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?

With no output schema, the description does explain result ordering, the truncation signal, and the positional meaning, which is the essential return-value context. It leaves the per-vessel field set and any pagination beyond 'truncated' unspecified, a modest gap for a vessel-list tool.

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 description coverage is 100%, so all eight parameters are already documented, including defaults for limit and max_age and the ship_type group convention. The description adds the box-area constraint that governs min/max lat/lon but says nothing extra about limit, max_age, ship_type, or speed, so baseline 3 is right.

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: 'Vessels inside a latitude/longitude box', plus the ordering ('newest report first') and that each is at its last reported position. That spatial-box phrasing implicitly separates it from radius-based siblings like vessels_near, but no sibling is named explicitly, so it stops just short of a 5.

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?

Gives real operating context for choosing and running it: per-plan box sizes (1/4/25/100 square degrees), free-account 24h delay and 1,000 credit cap, and 1 credit per vessel returned. It never explicitly says when to prefer a sibling such as search_vessels or vessels_near, so the when-not guidance is absent.

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