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

With no annotations at all, the description carries the full burden and does disclose genuinely useful operational traits: no API key, 30-minute cache (so data can be stale), and an x402 cost of $0.02/call in USDC on eip155:8453. It stops short of error behavior, units, or rate limits, but the cost/auth/caching disclosure is well above average for an unannotated tool.

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 provenance and payload, then cost/caching, which is the right order. One sentence is redundant and slightly malformed ('Use this when an agent needs to current conditions + 3-day forecast...') since it repeats the opening clause without adding information.

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 3-param, unannotated tool with no output schema, the description covers what is returned, both input modes, caching staleness and pricing. Remaining gaps (temperature units, error responses) are minor and not needed to invoke it correctly.

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 baseline would be 3, but the description resolves a real ambiguity in the schema: all three of city, lat and lon are marked required, while the city description says 'Or provide lat/lon instead'. The phrase 'by city name or coordinates' tells the agent these are alternatives, which the structured data actively muddles.

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 verb+resource (live weather from Open-Meteo) and enumerates exactly what is returned: current temperature, humidity, wind, conditions, plus a 3-day forecast. Two input modes (city name or coordinates) are named, which cleanly separates it from weather-adjacent siblings like live_air_quality and geo_time_sunrise_sunset.

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 offers a 'Use this when an agent needs...' clause, but that clause simply restates the purpose already given (current conditions + 3-day forecast) and adds no discriminating guidance. There is no when-not guidance and no pointer to alternative siblings (e.g. live_air_quality for pollution, geo_time_sunrise_sunset for solar data), leaving selection to inference.

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