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

Goes well beyond the annotations and even explains an anomaly in them: 'Reads or computes only; not marked read-only because each call is charged' directly resolves why readOnlyHint=false on a non-mutating tool. It also discloses data provenance (Norwegian Meteorological Institute), cost model ($0.002/call via x402 USDC or card key, first 25 free, failed calls free) and that the tool is not idempotent in practice because each call bills.

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?

Purpose and return contents are front-loaded, then provenance, use cases, example, and pricing in a sensible order; every sentence is a short clause rather than prose. The pricing/auth sentence is longer than strictly needed for tool selection, which keeps it from a 5.

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?

With no output schema, the description carries the return-value burden and does so by enumerating every field and the forecast horizon. Cost, auth path, data source, and failure billing are all covered; only minor items (forecast timezone/reference time, error semantics beyond 'failed calls free') are absent for a 3-parameter tool.

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 baseline is 3, and the description adds real value on top: a worked example (lat=59.33, lon=18.07, hours=12) showing how the three parameters combine, plus output units (Celsius, mm) that the schema does not state. It does not add further syntax or bounds beyond the schema's 1-48 default 12, so it is not a full 5.

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 concrete verb+resource ('Weather for any point on Earth by latitude and longitude') and enumerates exactly what is returned: temperature in Celsius, conditions, precipitation, wind, humidity, cloud cover, pressure, plus an hourly forecast up to 48h. Nothing in the sibling set (sun, moon, time, geocode, earthquakes) overlaps, and the distinction is obvious from the text alone.

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?

Gives a clear application context ('travel and event planning, logistics, agriculture and any agent that needs the weather'), which tells the agent when this is the right tool. It stops short of explicit exclusions or naming alternatives (e.g., sun/moon for astronomical data), so it lands at clear-context-no-exclusions rather than full routing guidance.

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