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

Goes well beyond the readOnly/idempotent/openWorld annotations: documents error semantics (404 place_not_found not charged, 5xx upstream errors not charged), pricing (USD 0.002), free-tier rate limit (5 per IP per UTC day), latency (0.1-2 s), data provenance/licensing, and accuracy caveats. This is exactly the behavioral context an agent needs.

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 purpose, then input contract, return shape, errors, pricing, and caveats in a tight sequence. It is dense but every clause earns its place; only mild risk of being read as a wall of text.

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 enumerates the return fields (location, updated_at, units, hourly rows, cached, attribution), covers input constraints, error paths, cost, and licensing obligations. Nothing an agent needs to invoke or interpret the call 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 baseline is 3, but the description adds real meaning: the lat+lon-vs-place exclusivity, the place matching rule ('City, CC' ISO codes, 15,000+ population), the default of 24 hours, and the not-charged 404 on no match. It reinforces and extends rather than merely repeats 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?

States a specific verb and resource ('hourly weather forecast for a point or a city') and specifies both accepted input modes. An agent immediately knows this retrieves forecast data and can tell it apart from the rest of the (non-weather) sibling set.

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?

Clearly explains the two mutually exclusive input modes (lat+lon together vs place alone) and gives an explicit when-not: not for safety-critical decisions, use official services instead. It lacks formal 'alternatives' routing, but no sibling weather tool exists to route to, so the guidance is essentially complete.

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