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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so safety is covered externally. The description adds genuinely useful behavior beyond that: gauge-matching logic with matched_by/query_location/distance_km, a 30 km coastal cutoff, a ~6-day forecast horizon with prediction_note, local-time interpretation, wind-surge fields, and attribution. However it never describes the actual response structure or empty/no-gauge outcomes, so it sits at a solid but not exemplary level for a tool with annotations covering safety.

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-loaded with purpose and routing, then structured into labeled sections (When to use / NOT / Required args / chain / anti-fab). It is long, but nearly every sentence carries actionable information; a few clauses (e.g., the anti-fab note and chain restatement) slightly overlap with earlier content.

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 6-param open-world read with no output schema, the description covers invocation, location resolution, date defaults and horizon, and names key response fields (forecast_cm, forecast_deviation, attribution), which is nearly complete. The main remaining gap is that the returned structure (per-station grouping, tide event list) is only sketched, not described.

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 baseline is 3, but the description adds real semantics: city first matches a gauge name, otherwise the place is geocoded and the nearest gauge by distance and district is chosen; station_limit default 3 (1–10); date defaults to today and the next two days; either city OR lat+lon is required. That is meaningful glue beyond the schema text.

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 first sentence names a specific resource (high/low tide for a coastal location, official BSH data with wind-surge forecast), which is precise and distinct from weather or routing siblings. It also frames it as the answer to 'when is low tide in X', making the resource unmistakable.

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?

Explicit 'When to use' with concrete example questions and 'When NOT to use' with named alternatives (get_current_weather, MobilityMCP, resolve_location) plus inland-location exclusions. It also documents the typical chain (search_place → this tool) and that one call covers one location/date-range.

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