Active National Weather Service warnings for any US ZIP code. Free weather_alerts tool.
Scored across 3 tools
sites_check and weather_alerts both return active alerts for ZIP codes, and sites_check accepts as few as one ZIP, creating real overlap for the common single-location case. The descriptions do clarify the intended split (batch up to 25 ZIPs vs. single-ZIP top 3), and state_alerts is clearly distinct, so the boundaries are workable but not crisp.
All names use snake_case and are readable, but the pattern is mixed: sites_check uses a noun_verb form while state_alerts and weather_alerts use noun_noun. The set does not follow a predictable verb_noun convention consistently.
Three tools is on the thin side but reasonable for a focused severe-weather alert server; each tool covers a distinct access pattern (single ZIP, batch ZIPs, statewide). It is not bloated, though a couple more capabilities could be justified.
The surface covers the core read-only alert workflows: single ZIP, batch ZIP list, and state-level filtering by event and severity. Minor gaps remain, such as coordinate/county lookup and retrieving full alert detail beyond the top 3 for a single ZIP, but agents can work around these.
PRO. Check up to 25 ZIPs (stores, job sites, fleet depots, properties) for active alerts at once, worst first.
| Name | Required | Description | Default |
|---|---|---|---|
| zips | Yes | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) | |
| min_severity | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose two real traits: a hard cap of 25 ZIPs and that results are ordered 'worst first'. It omits auth requirements, rate limits, what an 'active alert' comprises, and the response shape — substantial gaps for a mutation-free but non-trivial 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?
A single tight sentence that front-loads the core action and batch limit. The leading 'PRO.' token is unexplained filler that costs a bit of clarity.
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-parameter tool with no annotations and no output schema, the description leaves min_severity undefined, the response format unspecified, and auth expectations unstated. An agent could invoke it but could not confidently configure severity filtering or interpret results.
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 only 33%; only access_token is documented in the schema. The description never explains min_severity (its meaning, valid values, or default) even though 'worst first' hints at severity ordering, and it adds no detail on the zips array format beyond item count.
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: check up to 25 ZIPs (stores, job sites, fleet depots, properties) for active alerts. The parenthetical examples clarify what a 'site' is, which helps separate it from state_alerts/weather_alerts, though it never explicitly addresses those siblings.
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?
Implies batch usage via 'up to 25 ZIPs ... at once' and bulk-check intent, but gives no explicit guidance on when to pick this over state_alerts or weather_alerts, nor any prerequisites for calling it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
PRO. All active alerts in a state, filterable by event (e.g. 'Tornado', 'Flood', 'Heat') and severity, with instructions.
| Name | Required | Description | Default |
|---|---|---|---|
| event | No | ||
| state | Yes | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) | |
| min_severity | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description must carry the behavioral burden. It adds real context — the result is a list of *active* alerts delivered 'with instructions' (i.e., response includes guidance text) — but it never says the operation is read-only, what permissions or token tier ('PRO') are required, or anything about freshness/rate limits.
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?
One front-loaded sentence that names the resource, scope, and filters with zero padding. The only questionable token is the opaque 'PRO.' prefix, but it costs almost nothing in length.
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?
Four parameters at 25% schema coverage with no annotations and no output schema means the description should do more. It covers the domain well but leaves the 'PRO'/access_token relationship, allowed min_severity values, and response shape implicit.
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 only 25% (only access_token is documented), yet the description compensates for the important filters by naming the event dimension with concrete examples ('Tornado', 'Flood', 'Heat') and calling out severity filtering. It stops short of explaining what values min_severity accepts, which matters since there are no enums.
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 resource and scope: active alerts in a given state, optionally filtered by event type and severity. An agent can tell what it returns, but nothing distinguishes it from the sibling weather_alerts tool, which sounds closely related.
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 word 'filterable' implies the optional filters, and 'PRO.' hints at a gated/subscriber tier, but there is no explicit when-to-use guidance, no statement of when not to use it, and no routing versus weather_alerts or sites_check.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
FREE. Active National Weather Service alerts (warnings, watches, advisories) for a US ZIP code — top 3 by severity.
| Name | Required | Description | Default |
|---|---|---|---|
| zip | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose two genuinely non-obvious behaviors: results are capped at the top 3 by severity, and only currently active alerts are returned. It does not cover authentication, rate limits, or what an empty response looks like, but the truncation disclosure is the critical piece an agent would otherwise get wrong.
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?
A fragment plus one sentence, with the cost marker and the resource front-loaded and the severity cap placed last where it reads as a qualifier. Nothing is wasted and nothing is buried.
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 one-parameter, read-only lookup with no output schema and no annotations, the description covers what it fetches, the geographic scope, the alert categories, and the result cap. That is everything an agent needs to decide to call it and to interpret a short result set 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?
The schema gives the single 'zip' string parameter no description at all (0% coverage), so the description must compensate; it specifies 'US ZIP code', telling the agent the expected locale and identifier type. It stops short of stating the format (5-digit vs ZIP+4) or how to handle non-US or invalid inputs.
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 resource (active National Weather Service alerts, with the alert types named) and a specific scope (a US ZIP code, top 3 by severity). It is clearly distinguishable in spirit from state_alerts, but it never names or contrasts with that sibling, which keeps it out of the top band.
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?
Usage is only implied: 'for a US ZIP code' suggests this is the ZIP-based path while state_alerts is presumably the state-based path, but the description never states when to prefer one over the other or any exclusions. The 'FREE' marker hints at a cost trade-off but is not framed as guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
sites_checkstate_alertsweather_alertsActive weather alerts and warnings from the National Weather Service
US NWS weather alerts and 5-day forecasts for AI agents. $0.01 per call.
US weather alerts (NWS): warnings, watches. $0.01/query. Register in-session — free testnet funds.
Get US weather forecasts, active alerts, and current observations.
Add one secure layer between your agents and this server.