Get official weather and disaster warnings

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds behavior the annotations cannot: it runs the Apify Actor tacps126/alerts-radar on the caller's account, costs about $0.002 per alert with a $0.5 per-call spend cap, and returns results most-severe-first. The billing/spend-cap disclosure is exactly the kind of consequence an agent needs before invoking.

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 core claim, then sources, then returned fields, then ordering and cost – a sensible information hierarchy. The parenthetical source list is dense but each item earns its place by establishing coverage; only the duplicated 'plus worldwide'/'plus' phrasing is slightly loose.

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 8 optional params, a full output schema and rich annotations, the definition supplies what structured data cannot (sources, ordering, cost, actor identity). The one substantive gap is filter-combination semantics across the four geographic/hazard arrays, which an agent must guess.

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 per-parameter documentation is already handled by the schema and the baseline of 3 applies. The description adds only indirect semantics – 'Most severe first' hints at ordering despite min_severity, and nothing clarifies how areas/states/countries/hazards combine (AND vs OR), which is the real ambiguity.

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 ('Official warnings in force') and pins it down with the exact issuing sources (NWS, MeteoAlarm, NDMA/IMD/CWC, INMET, GDACS, USGS) and the returned fields. An agent can tell this is an authoritative-alerts aggregator and not a generic government-document search like search_gov_updates, 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?

The phrase 'in force' and the source list imply the use case (current official hazard warnings), but there is no explicit when-to-use/when-not statement and no named alternative among the siblings (e.g. search_gov_updates). Usage is inferable rather than instructed.

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