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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely non-derivable context: the geographic constraint (Ireland-only, WGS84), the data provenance (GeoHive, SMR, NPWS), the 500 m search radius for monuments, and the warning that results are not live observations. It does not mention caching, freshness windows, or behavior for points outside Ireland, which keeps this at 4.

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?

Two sentences, front-loaded with the result scope, then the exclusion/routing clause. The long enumeration is dense but each item is decision-relevant, so little is wasted; the only minor cost is that it reads as a catalogue rather than a terse directive.

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?

An output schema exists, so return formatting need not be described, and the description covers the dataset union, coordinate frame and scope well. The residual gap is what happens for coordinates outside Ireland and whether output is truncated by the token budget — relevant given the max_tokens parameter, though hinted at.

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 100%, so the baseline is 3. The description lifts it by specifying the coordinate reference frame (WGS84) and the Irish coverage area, which the schema's bare lat/lon numbers and bounds do not convey. Forecast hours and token budget are already fully documented in the schema.

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 enumerates exactly what is returned for a WGS84 point in Ireland: administrative units (county, local authority, constituency, electoral division, small area, settlement via GeoHive), the nearest Met Éireann station and forecast, SMR monuments within 500 m, and NPWS protected sites. An agent can tell precisely what this tool produces without opening the schema, and the sibling ireland_call is explicitly named for other data types.

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?

It gives both sides of the routing decision: what is in scope, and an explicit exclusion list ("Not live observations, river levels, buoys, bikes or populations") paired with the alternative to use instead (ireland_call). This is exactly the when/when-not/alternative structure that lets an agent pick the right sibling.

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