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

Annotations cover the read-only/idempotent safety profile, and the description still adds critical context beyond them: heights are relative to MEAN SEA LEVEL not chart datum, an explicit 'never use for navigation' warning, an auth requirement (API key on a paid Tides plan), and default date-range behavior. This is rich behavioral disclosure.

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 and return shape, then usage routing, then the datum caveat and auth/default facts. Dense but every sentence carries distinct, non-redundant information; no filler.

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, and the description compensates by describing the returned event list and height units. Combined with full schema coverage and annotations, an agent has everything needed to call and interpret the 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 coverage is 100% so the schema documents each parameter, but the description adds default values not in the schema (from today, 2 days or the plan's limit) for start_date/days. It does not add format or syntax detail for tz/lat/lon, so it is a modest improvement over the baseline 3.

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 (returns high/low water times and heights), names the data source (FES2022), and specifies the return shape (events with type, time, height_m). It explicitly differentiates from the two nearest siblings, get_tide_heights and get_tide_window.

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 an explicit when-to-use ("when high or low tide is") plus named alternatives with the condition that selects each: get_tide_heights for a continuous curve, get_tide_window for tides with sun/moon context. Nothing is left to inference.

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