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

Annotations only declare readOnly/openWorld/non-idempotent; the description adds behavior the agent cannot infer: each call costs USDC from a configured wallet, charges are bounded by session/daily budget caps, non-US points are refused at no cost, and results are third-party data rather than instructions (an explicit prompt-injection warning). That is substantial disclosure beyond the annotations.

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 the highest-stakes facts (US-only, paid, third-party data) before the product menu, and the menu format is compact and scannable with prices and required-param markers. However, multiple product lines are cut off mid-sentence ('for a foreca...', 'temperature, dewpoint...'), which is wasted or lost content rather than true conciseness.

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-product tool with no output schema, it covers payment mechanics, budget caps, refusal behavior, and a brief return sketch for each product. Gaps remain: the truncated product descriptions leave some return contents and required params ambiguous, and no latency/rate-limit behavior is mentioned.

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%, but the schema itself defers parameter naming to the description ('names listed in the description'), so the per-product param lists (state*, lat*, lon*, stationId, wfo, gridX/gridY, fields, hours) are load-bearing. Several entries are truncated mid-list, so the enumeration is not fully reliable.

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 opening sentence names the provider (US National Weather Service), the resource types (forecasts, observations, alerts) and the geographic scope, and the product list enumerates exactly what each call returns. An agent can distinguish this from siblings like market_quote or open_data_search 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?

It states scope constraints (US points only, out-of-US refused free) and pricing per call, and notes that weather.noaa gives the same answer as weather.forecast, which routes between two products. It stops short of explicit when-to-use-this-vs-sibling guidance relative to call_product or get_price_quote.

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