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

Annotations are present (readOnly, openWorld, idempotent, non-destructive), but the description adds substantial context beyond them: cost, the x402 paywall handshake, 10-minute caching per query, required attribution string, licensing, and which provider returns alerts. This is exactly the extra behavioral detail the annotations cannot express, and nothing contradicts them.

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 the one-line purpose before elaborating on sources and payment. It is dense but nearly every clause carries information; the main redundancy is the price/payment restated at both start and end, which slightly pads an otherwise information-rich paragraph.

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 paid, multi-source tool with no output schema, the description covers what an agent needs: the payment flow, geographic routing logic, return fields (provider, attribution), caching, and provider-specific limitations. Nothing material 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 description coverage is 100%, so the schema already documents every parameter including aliases, ranges, and the U.S.-only caveat. The description restates much of this (lat/lon vs location, forecast_days, alerts U.S./NWS-only) rather than adding syntax or format detail. Baseline 3 is appropriate since the structured schema does the heavy lifting.

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 and scope: "Current conditions + short forecast, worldwide." It is immediately distinguishable from weather_preview via the explicit paid marker ("[PAID — 0.004 USDC on Base via x402]") and names its data sources (NWS + MET Norway). An agent can tell what it does and that it differs from the free preview sibling without opening the schema.

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?

Provides strong routing guidance: U.S. coordinates go to NWS with alerts, everything else to MET Norway without alerts, and it explains that address resolution is U.S.-only ("non-U.S. place names are never resolved this way"). It also explains the unpaid-first workflow. It stops short of explicitly naming weather_preview as the free alternative, so it lacks a true when-not clause.

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