Weather & Climate Intelligence MCP

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

With no annotations, the description carries full behavioral burden and does so thoroughly. It discloses the paid nature ($0.01 per query after 50/day free), the 402 error handling flow (pay memo, re-call with payment_tx), and the authentication bypass via Bearer key. It also outlines what data the tool returns, providing a clear operational picture.

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?

The description is succinct and front-loaded with the core purpose. The first sentence lists key outputs in a compact series, and the second paragraph contains only essential payment/auth instructions. Every sentence earns its place with no fluff or repetition.

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?

Given the presence of an output schema, return values need no further explanation. The description covers the tool's purpose, output scope, payment model, error handling, and authentication—making it fully self-contained for an agent to select and invoke it 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?

Schema coverage is 100%, so the schema already documents all parameters. The description adds meaningful context beyond the schema by explaining the 402 re-call flow with 'SAME args plus payment_tx=<signature>', which clarifies when and how to use payment_tx. It also references the free-tier allowance, complementing the agent_id schema description.

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 description opens with a specific verb and resource: 'Get the agricultural weather outlook for a location from Open-Meteo.' It enumerates the distinct outputs (growing degree days, frost risk, soil moisture/temperature, precipitation outlook, planting-window assessment), which clearly differentiates it from siblings like current_weather, forecast, and historical_weather.

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 description clearly conveys that this tool is for agricultural weather planning, implying the appropriate context (farming, growing conditions). It does not explicitly state when not to use it or name alternative tools, but the specialized scope is unambiguous enough for an agent to select it correctly.

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

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

No annotations are provided, so the description fully discloses behavior: the paid nature ($0.50), default date (today UTC), error handling for 402 with a retry pattern, and an auth bypass. It also clarifies the output format ('structured JSON', 'no prose'). This goes well beyond what structured data would show.

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?

Two concise paragraphs front-load the core purpose, then layer the necessary payment and error-handling details. Every sentence serves a purpose—no filler or redundant repetition of schema fields.

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?

Given the tool's complexity (paid access, 402 retry, auth bypass, default date, output format), the description is complete. It names the sibling daily_brief as the full alternative, describes the output shape, and covers error recovery. An output schema exists, so detailed return documentation is unnecessary.

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 baseline is 3. The description adds only marginal value: it reaffirms the date default, explains payment_tx usage in the 402 retry, and mentions the auth header (which is not a parameter). It does not radically improve understanding beyond the schema's existing descriptions.

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 description opens with a specific verb and resource: 'Get the top 5 signals from today's brief as structured JSON'. It differentiates from the sibling daily_brief by calling itself a 'cheap sample of the full daily_brief' and states the intended use case: 'decide whether to buy the full brief'.

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 explicitly frames this as a preview tool ('so an agent can decide whether to buy the full brief'), clarifying when to use it. It also provides handling for payment flows ('On a 402, pay the returned payment memo and re-call...') and a bypass alternative ('An Authorization: Bearer fnet_ key bypasses payment.').

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

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

With no annotations, the description carries full behavioral disclosure. It explicitly reveals the paid nature, free allowance, 402 payment flow, payment_tx parameter semantics, and the Bearer key bypass. It does not discuss error handling for invalid coordinates, but the payment and retry behavior are well disclosed.

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?

The description is compact and well-structured, with the first paragraph defining the tool's data output and the second paragraph covering payment/auth details. Every sentence contributes either functional or operational information, without fluff.

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?

Given the presence of an output schema, the description need not detail return structure. It covers data contents, source options, token configuration, free-tier limits, paid behavior, and 402 handling, providing a complete picture for a paid retrieval tool.

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 input schema already describes all 5 parameters, so the baseline is 3. The description adds important semantic context for payment_tx by explaining the 402 re-call flow with 'SAME args' and the signature, which goes beyond the schema's simple description. It also clarifies the month parameter's optionality and scope.

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 description opens with 'Get climate normals for a location' and specifies the exact resource (multi-decade monthly climate data averages, frost probabilities, growing degree days). This clearly distinguishes it from sibling tools like current_weather or historical_weather, which concern immediate or past weather rather than long-term normals.

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 description outlines when to use the tool (for climate normals) and provides context about data sources (Open-Meteo vs NOAA normals) and payment requirements. It does not explicitly state when not to use or name alternatives, but the nature of the data strongly implies appropriate use cases.

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

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

No annotations are provided, so the description carries the full burden. It discloses the data source (Open-Meteo), the free tier, and the set of returned weather fields. However, it does not mention behavioral nuances such as geocoding fallback, units, rate limits, or error handling. For a simple read-only lookup, this is adequate but not rich.

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?

The description is two sentences with no waste. The main verb and resource come first, and every phrase (data fields, FREE, location options) earns its place. It is front-loaded and easily scannable.

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?

The tool has an output schema, so return values need not be explained. The description covers the input options, data source, and scope ('current'). It is complete for a simple lookup, though it could mention precedence if both city and coordinates are provided; the 'either...or' phrasing largely covers this.

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% (all parameters described), but the description adds value by clarifying the relationship between parameters: 'either latitude+longitude or a city (optionally with state/country)'. This helps the agent understand mutual exclusivity and optional disambiguation, which goes beyond the individual property descriptions.

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 description has a specific verb 'Get' and resource 'current weather', and it explicitly lists the data fields (temperature, feels-like, humidity, wind, conditions, cloud cover, visibility). This clearly distinguishes it from siblings like forecast, historical_weather, and weather_alerts.

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 specifies the input format ('either latitude+longitude or a city optionally with state/country') and clarifies the tool is for current conditions. While it doesn't explicitly name alternatives or exclusions, the 'current' qualifier and sibling names provide clear context for when to use this tool versus forecast or historical tools.

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

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

With no annotations, the description fully discloses behavioral details: it is a paid tool, expires at midnight UTC, supports a retry flow on 402 with payment_tx or stripe_token, includes provenance attestation, and offers a Bearer auth bypass. This richly conveys the tool's operational behavior.

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?

The description is well-structured: first paragraph defines what the brief contains and its provenance, second paragraph covers payment and expiration. Every sentence delivers necessary information without padding or redundancy.

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 complex commercial tool, the description covers all essential operational aspects: contents, data sources, payment model, expiration, retry logic, and authentication alternatives. The presence of an output schema means return value details are not needed, but behavioral completeness is exceptional.

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?

Input schema descriptions already cover 100% of parameters, but the description adds meaningful usage context beyond schema: it explains the 402 retry flow ('pay the returned payment memo and re-call with the SAME args plus payment_tx') and mentions the Authorization Bearer bypass, which clarifies how to use payment-related parameters in practice.

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 description clearly states the tool fetches a 'curated daily weather-intel brief' with a specific list of contents (alerts, events, forecast, agricultural signals). It distinguishes itself from siblings by emphasizing the daily, consolidated nature, making its purpose unmistakable.

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 description gives clear context on when to use the tool (for a daily comprehensive brief) and mentions expiration and payment retry logic, but does not explicitly contrast with alternatives like 'current_weather' or 'forecast'. There is no explicit when-not-to-use guidance, but the use case is well implied.

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

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

No annotations provided, so description carries full burden. It discloses pricing model ($0.005/query, free allowance), payment flow on 402, agent_id scoping for allowance, and bearer key bypass. Also describes data coverage and resolution. This is exceptional transparency beyond the basic purpose.

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?

Two concise paragraphs: first front-loads the core purpose, second covers billing/auth. Every sentence adds necessary information; no fluff or repetition. Well-structured for quick parsing.

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?

Despite having no annotations, the description covers all critical context: data range, cost, auth, payment retry, and allowance scoping. Output schema exists, so return value details are covered separately. Description is fully sufficient for an agent to use the tool 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?

Input schema has 100% coverage with descriptions for all parameters. The description mostly repeats parameter roles (agent_id, payment_tx) already in the schema, adding no new semantic detail. Baseline of 3 is appropriate as the 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?

Clearly states it provides weather forecasts from Open-Meteo with specific temporal scope (up to 16-day daily and 48-hour hourly). Distinguishes from siblings by mentioning both daily and hourly data, and differentiates from current_weather or historical_weather.

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?

Gives clear context: use for weather forecasting, with cost guidance ('cheap enough to call constantly'). Does not explicitly mention alternatives or when not to use, but the purpose is unambiguous and implies when this tool is appropriate.

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

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

With no annotations, the description takes on the full transparency burden. It discloses non-obvious billing behavior ($0.01/query after a free allowance), the exact 402 retry flow (pay memo, re-call with same args + payment_tx), and the Bearer key bypass. This goes well beyond the schema and gives an agent actionable cost/error-recovery context.

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?

The description is exceptionally concise: one sentence for tool purpose and one for billing/payment behavior. Every clause earns its place, and the most important information (purpose) is front-loaded. No redundant or filler content.

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?

Given the output schema exists to document return values and there are no annotations, the description is complete enough. It covers the tool's core behavior, data granularity, payment/retry logic, and auth bypass. No significant missing context for an agent to select and invoke the tool 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?

Schema description coverage is 100%, so the baseline is 3. The description's prose (location, date range, payment_tx) largely restates what the schema already defines. It adds only minor value by clarifying that the retry should use 'SAME args plus payment_tx', but otherwise does not enrich parameter meaning.

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 description uses a clear verb ('Get') and resource ('historical weather') with explicit scope: 'location and date range.' It lists the exact data variables (high/low/mean temperature, precipitation, max wind) and differentiates from siblings by highlighting 'historical' and 'archive' (vs. current, forecast, normals).

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 description clearly implies when to use this tool (for past weather data from an archive), which distinguishes it from current_weather/forecast/climate_normals. It does not explicitly name alternatives or exclusions, but the billing and 402 retry instructions provide clear operational 'when' guidance for edge cases.

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

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

With no annotations provided, the description carries the full burden. It transparently states this is a free info endpoint and enumerates what it returns. It doesn't explicitly state 'read-only' or 'no side effects,' but the informational nature is evident. It also adds context about provenance attestation, which is useful behavioral detail beyond just a bare listing.

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?

The description is compact and informative, front-loading the key fact ('FoundryNet Data Network info + provenance attestation details') and then expanding with specifics. Every sentence contributes meaningful content with no padding or redundancy.

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 tool with no parameters and an output schema, the description is complete. It tells the agent what the tool provides, why it's relevant (attestation), and lists the sister servers. Combined with the output schema, the agent has enough context to invoke the tool 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 tool has zero parameters, so the baseline is 4. The description doesn't need to explain parameter syntax or meaning. It adds no param-specific info, but none is required.

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 description uses a specific verb ('Returns') and identifies a clear resource (FoundryNet Data Network info + provenance attestation details). It lists concrete deliverables (how to attest, endpoint, sister servers), making it unmistakably distinct from the weather-focused sibling tools.

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 description implies the usage context: use this tool when you need attestation details or information about sister data servers. It doesn't explicitly name alternatives or exclusions, but the sibling tools are all weather-related, so the differentiation is clear from context.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains the score range, the inclusion of endpoint threats, and the shipment recommendation. Notably, it discloses the paid-call model, the daily free allowance, the 402 retry procedure with payment_tx, and the bearer-key bypass, which are important behavioral traits that the agent must know for successful invocation.

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?

The description is very concise and front-loaded, with the core purpose in the first sentence and necessary payment details in a separate paragraph. Every sentence serves a purpose: the first explains the tool's function, the second provides essential billing and error-recovery instructions. No wasteful wording exists.

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?

The description covers the key operational aspects: what the tool does, the score range, the output components (threats, recommendation), and the payment/retry behavior. An output schema exists, so return values need not be re-explained. It is complete for most usage scenarios, though it could briefly mention when this tool is preferable to simple weather lookups or vice versa, but that gap is not severe.

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 description coverage is 100%, so the baseline is 3. The description adds context that origin and destination are the endpoints of the shipping route and clarifies the role of payment_tx in the retry flow after a 402. However, it does not add substantial meaning to the individual parameters beyond what the schema already provides, making a 3 appropriate.

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 description opens with a precise action: 'Score weather risk along a supply-chain / shipping route (0-100) with the specific threats at each endpoint and a shipment recommendation.' This clearly states the tool's specific verb and resource, and distinguishes it from sibling tools like current_weather or weather_alerts by emphasizing the route-based risk score that combines origin and destination.

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 description implies when to use the tool (for transport/shipping risk assessment) by explaining it combines current conditions and NWS alerts at both endpoints, but it does not explicitly contrast it with alternatives like weather_alerts or forecast, nor does it state when not to use it. The payment handling instructions are operational but not selection guidance. This is implied usage, not explicit.

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

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

With no annotations, the description carries full burden. It discloses payment behavior (cost per query, free allowance, 402 handling with payment_tx and auth bypass), which is critical and goes beyond typical expectations. It also specifies output style 'not prose' and the data sources. This is excellent transparency.

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?

The description is two paragraphs and front-loaded with the core purpose. The payment instructions are necessary but add length; however, they are clearly separated and earn their place. It is dense but not verbose, so a score of 4 is appropriate.

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?

The tool has an output schema and 7 parameters, so the description doesn't need to detail return values. It covers core functionality, payment flow, and output style. Interesting edge cases like free quota exhaustion and payment retry are addressed, making it quite complete. Slightly more could be said about error conditions beyond 402, but overall strong.

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 43% (3 of 7 params described). The description adds meaning to origin/destination by labeling them in the comparison context and explains payment_tx's role in 402 handling, but it does not describe coordinate formatting or units. It partially compensates for low schema coverage, but not fully.

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 description clearly states the tool compares weather between two locations for trip planning, listing specific outputs (forecast, temp/precip deltas, advisories, packing recommendations). This distinguishes it from sibling tools like current_weather or forecast, which address single locations. The verb 'compare' and resource 'weather between two locations' are specific and unambiguous.

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 description gives clear usage context: 'for trip planning' and 'origin vs. destination' indicate when this tool is appropriate. It does not explicitly name alternatives or exclusions, but the purpose is distinct enough that an agent can infer when to use it versus single-location weather tools. A score of 4 reflects clear context without explicit alternative mentions.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It adds useful context: 'FREE — public safety' and 'reserved' for radius_km, and it implies read-only behavior through the verb 'check.' It doesn't mention rate limits or return format, but the output schema covers the return, so the description provides sufficient transparency for a low-risk read 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?

The description is two sentences, front-loaded with the core purpose, and uses efficient, no-waste language. Every clause adds value: source, cost, safety, and query modes are all covered in one compact statement.

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?

Given the tool's simplicity, an output schema exists, and the description covers purpose, data source, and query variants, it is almost complete. It does not mention any caveats (e.g., limitations on 'reserved' radius_km), but the description already flags radius_km as reserved, and with no required parameters, the tool is fully usable based on this text.

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 input schema already describes all four parameters (state, latitude, longitude, radius_km) with 100% coverage. The description reinforces the query modes but adds no new parameter-level detail beyond what the schema provides, so the baseline of 3 is appropriate.

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 description clearly states the tool's specific function: 'Check active severe-weather alerts from NOAA/NWS (US).' It distinguishes itself from sibling tools by focusing on severe-weather alerts rather than current conditions, forecasts, or climatology, and it names concrete query modes (state, lat/lon, nationwide).

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 explicitly tells when to use the tool: 'Query by state code, by latitude+longitude (point), or with no args for nationwide weather alerts.' This provides clear usage context, though it does not explicitly name alternatives or exclusions (e.g., 'use this instead of forecast'), so it misses a direct comparison. Still, the scope is well-defined.

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