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

Annotations already carry readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds valuable non-obvious behavior: the 1-year request cap, the hilo vs 6min return granularity, the H/L tide-type coding, and the MLLW datum default rationale. No contradiction with annotations — 'predictions' aligns with readOnly semantics.

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?

Five sentences, front-loaded with the core purpose, then layering return format, datum, constraints, and routing. Dense but each sentence earns its place — the only minor issue is the paragraph wall could use slight structural separation, but nothing is wasted.

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 7-parameter tool with a rich schema and an output schema (so return values need not be spelled out), the description covers the critical operational constraints: date-range cap, interval modes, datum meaning, and the prerequisite station-ID resolution. Moderately complex tool, and nothing an agent needs to call it correctly 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 100% with detailed per-parameter descriptions and enums, so the schema carries the load — baseline 3 is appropriate. The description does add a touch of context (MLLW as US chart datum, hilo vs 6min behavior), but these largely echo the schema's own parameter descriptions, so marginal value above baseline.

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+resource: 'High/low tide predictions for a CO-OPS tide station over a date range.' It clearly differentiates from siblings by naming the data type (tides) and the station source (CO-OPS), letting an agent distinguish it from get_water_level, get_currents, and get_conditions without opening schemas.

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 pre-usage routing: 'Use noaa_marine_find_stations first to resolve a station name or location to a numeric station ID.' Also flags the 1-year date-range limit and directs splitting longer ranges. It lacks explicit when-not-to-use guidance versus the water_level sibling, but the resolution step and limit are clear, actionable context.

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