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

Annotations already cover read-only, idempotent, open-world and non-destructive behavior, yet the description still adds real value: data source (MET Norway Locationforecast 2.0 hourly precipitation), that it is a model forecast rather than radar nowcast, UTC timestamps, and a 1-credit cost. These are behaviors an agent could not infer from the annotations, though it says nothing about handling missing data or out-of-range hours.

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 answer to "what does it return" is front-loaded, followed by use case, data source, prerequisites and cost in a logical order with no wasted clauses. The "walk, run, school run" list is slightly padded but earns its place as usage framing.

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 three-parameter, no-output-schema tool, the description covers everything needed: what is returned (wet/dry, first wet hour, total, hourly amounts), the horizon limit, units/timezone, data provenance and the coordinate prerequisite. Nothing essential for correct invocation is missing.

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 defines lat, lon and hours. The description still adds meaning by framing the time horizon as 1-12 hours and by directing the agent to geocode/postcode_lookup to fabricate valid coordinates for UK place names, which is genuine guidance not present 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 names a specific question ("will it rain?"), a specific resource (hourly precipitation forecast), and a bounded scope (next 1-12 hours, hourly amounts plus first wet hour). It also distinguishes itself from adjacent concepts by calling out model forecast vs. radar nowcast, separating it from nowcast/historical siblings like rainfall_last_24h.

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 concrete usage contexts (walk, run, school run, outdoor job) and an explicit prerequisite chain: for a UK place name or postcode, resolve coordinates via geocode or postcode_lookup first. It lacks an explicit "do not use this for X" statement pointing at the generic weather or cloud_cover_forecast siblings, so it falls short of the top band.

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