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

The annotations declare readOnlyHint=true and idempotentHint=true, which already indicate a safe, non-mutating operation. The description goes beyond this by clarifying time zones (ISO 8601 with station UTC offset), height units (feet vs metres depending on station region, overridable via units), and the chart datum reference. These add genuine behavioral context not present in annotations.

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 description is a single, well-structured paragraph that front-loads the core function (high/low tides) before adding unit/zone details. Every sentence earns its place, and there is no redundant restatement of the title or schema. It is concise but informative, though slightly dense.

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?

Given there is no output schema, the description effectively communicates the return content (high/low times and heights, plus current height/direction) and key data formats. It addresses units and time zones, which are critical for correct interpretation. For a moderate-complexity read-only tool, this is fairly complete; missing details like error behavior are not essential.

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 50%: date and station_id have descriptions, but days and units lack them. The tool description adds important semantics for units (feet vs metres based on station, unless overridden) and mentions the days concept ('over one or more days'), but does not explain the days parameter's default, range, or meaning beyond that. It partially compensates for the schema gaps but not fully.

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?

The description clearly states the tool returns high/low tide times and heights for a single station over a date range, plus current height and direction when appropriate. This is a specific verb+resource combination that distinguishes it from siblings like search_stations (finding stations) and get_conditions (likely weather).

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?

The description says the tool works 'for one station' and implies the station must be identified, but it does not explicitly state when to use this tool versus search_stations (e.g., 'use search_stations to find station_id first') or mention exclusions. The schema notes station_id comes from search_stations, but that's not in the description itself, so routing guidance is only implicit.

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