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

Annotations already cover readOnly/idempotent/non-destructive/open-world, so the description's added value is the credit cost, the upstream source (Environment Agency real-time flood-monitoring API), the 6-hour staleness flag, and the caveat that some gauges don't report flow. It does not say what the nearby-search response looks like or how many readings come back, which is a modest remaining gap given there is no output schema.

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 the resource and the two modes, then the operational caveats and cost. The 'kayakers, canoeists and anglers' sentence is audience flavor rather than instruction, but it is short and does convey the practical use case, so little 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?

Covers retrieval mode, units, data source, freshness caveat, coverage limitation, and cost — everything needed to call a 5-parameter, all-optional read tool correctly. Return shape is only implied, but with no output schema and full parameter documentation the description is sufficient.

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 already documents all five parameters including their ranges and defaults. The description reinforces the station_id vs lat/lon exclusivity but says nothing about limit or dist_km, so it adds little meaning beyond the structured fields — the 3 baseline applies.

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 resource (river flow in cumecs) and two retrieval modes (single gauge vs nearest gauges to a point). The word 'flow' plus 'cumecs' cleanly separates it from the sibling river_level_now, so an agent can pick between level and flow without opening either 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?

Explicitly tells the agent to pass station_id for one gauge or lat/lon for a nearby search, and warns that only some gauges measure flow and that readings older than 6 hours are flagged stale. It never names an alternative sibling (e.g. river_level_now, river_stations_on_river) as the fallback, so there is clear context but no explicit either/or routing.

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