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

Annotations already cover read-only, idempotent, non-destructive and open-world traits, yet the description adds substantial operational context beyond them: header-based auth, per-resolution time caps, a 200-point-per-call ceiling, credit cost of 1 per vessel-day, plan rate limits, and a 24-hour delay on recent data for plans without live data.

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 purpose, then auth, then resolution/limits, then result semantics and archive caveats in a single dense paragraph. Every clause carries actionable information, though the run-on length slightly hurts scannability.

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 still explains the response shape (rows of time, lat, lon, speed_kn, course_deg) and the two metadata fields sources_through and pending_days, including the key caveat that missing days may reflect non-delivery rather than absence. Nothing essential for correct invocation is missing.

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% (mmsi and the resolution enum carry no descriptions), and the description compensates by explaining what each resolution means and its maximum span (raw up to 24 h, 1m up to 7 days, 1h up to 366 days). It also defines the returned row tuple, though it never clarifies mmsi or reinforces the from/to semantics beyond the schema examples.

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 ('where a ship has been between two times') plus the data provenance (AIS Trail archive) and time basis (UTC ISO 8601). This clearly separates it from get_vessel (current/static state) and vessel_port_calls without the reader opening any schema.

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 explicit preconditions and an exclusion: an AIS Trail API key must be sent as an Authorization header, and OAuth-only web connectors cannot use it yet. It does not name a sibling alternative for agents that lack a key (e.g. get_vessel for last known position), so it stops short of full routing guidance.

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