Weather & Geo Intel MCP

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

The annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered structurally. The description adds the upstream source (USGS feed), which is useful context, but says nothing about feed freshness/lag, result ordering, or truncation behavior under the limit.

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 compact sentences, front-loaded with what the tool returns and followed by the filter surface. The final clause enumerating returned fields ('magnitude, place, time, depth and coordinates') is wasted since an output schema already exists, but the overall size 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?

Scope, source, filters, and defaults (via schema) are all available, and the output schema removes any need to describe return values. The only substantive omission is operational behavior such as feed lag and ordering, plus the inaccurate bounding-box claim.

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 baseline would be 3, but the description claims the agent can filter by 'a bounding box' while the schema exposes only lat/lon/radius_km — there is no bounding-box parameter. This actively misdescribes an invocation option an agent might attempt, offsetting the correct mentions of magnitude, days, and radius.

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 and resource ('List recent earthquakes worldwide') plus the data source ('USGS feed'), which is exactly what an agent needs to recognize this tool. No sibling offers earthquake data, so no disambiguation is required, and the scope is 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 names the available filters (magnitude, days, point+radius), which implies the situations the tool fits, but never states when to prefer it or any exclusions/preconditions. With no competing sibling and all parameters optional, the omitted 'when to use' is low-impact but still a gap.

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?

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so safety is covered. The description adds genuine context beyond them: the upstream provider (USGS), the US-only coverage limit, and the dual feet/meters output. It does not say what happens for out-of-coverage coordinates (error vs. null), which keeps it from a 5.

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 sentences, zero filler, and the essential scope and source information is front-loaded before the return-value note.

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 an output schema present and annotations covering the safety profile, the description need only supply scope and semantics, which it does. The only missing piece is edge-case behavior for coordinates outside US coverage.

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% and both parameters are fully documented in the schema, including the example value and the US-coverage caveat on lat. The description only restates 'latitude/longitude' with no added syntax or format detail, so the baseline 3 applies.

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 (Get), resource (ground elevation), and inputs (lat/long), plus the data source (USGS Elevation Point Query Service) and return units (feet and meters). No sibling tool in the list returns elevation data, so it is trivially distinguishable from geocode, weather_*, and earthquakes.

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 implied rather than stated: an agent infers it should call this when it needs terrain elevation. There is no explicit when-to-use vs alternative guidance, though the 'within the US' scope constraint is a useful boundary. Adequate but with a clear gap.

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?

Annotations already declare readOnly, idempotent, openWorld and non-destructive behavior, so the safety profile is covered. The description adds real context beyond that: the US Census data source, the geographic restriction to US locations, and the important behavioral detail that a place name returns the city centroid rather than a point address.

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?

Three sentences, zero filler, with the core capability and accepted input formats front-loaded before the workflow guidance and the US-only constraint. Every sentence carries distinct information.

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?

An output schema exists, so return values need not be described. The description covers accepted input forms, data source, geographic scope, place-name return semantics, and where the tool fits in the weather/elevation workflow – everything needed to 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% and there is a single parameter, so the baseline is 3. The description goes beyond the schema by clarifying the semantic difference between the two accepted input shapes, notably that a city/town name yields a centroid rather than a rooftop-level point.

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 (convert) and resource (US street address or city/town name into lat/long coordinates), and names the data source (US Census). It clearly distinguishes itself from siblings weather_forecast, weather_current, weather_alerts, earthquakes and elevation by being the coordinate-lookup step.

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?

Explicitly says when to call it ('Call this first whenever you have a location as text and need coordinates') and names the downstream tools that consume its output (weather or elevation). It also states a hard exclusion: 'US locations only.'

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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds the useful 'active' filter constraint, but its return-value detail (event type, severity, headline, area, expiry) largely duplicates the existing output schema rather than disclosing new 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?

Two sentences with zero waste: the primary action and scope lead, the calling convention follows, and the return summary closes. Every clause earns its place.

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 a rich annotation set, a fully described single parameter, 100% schema coverage, and an output schema that carries return structure, the description supplies everything an agent needs to select and invoke the tool. Nothing material 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 the single 'area' parameter and even notes that full state names are accepted. The description's examples (CA, TX, FL) and mention of marine areas add marginal value, but its 'two-letter state code' framing is slightly narrower than the schema, so it does not exceed baseline.

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 and resource ('List active NWS weather alerts') plus the scope (US state or marine area) and enumerates the alert categories covered. It clearly distinguishes itself from weather_forecast and weather_current siblings without needing to name them.

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 implied through the required input ('Pass a two-letter state code like CA, TX, FL'), which tells the agent how to call it, but there is no explicit statement of when to prefer this over weather_current or weather_forecast, and no exclusions or prerequisites.

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?

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so safety is covered. The description adds genuinely new behavioral context: results come from the nearest NWS station and coverage is US-only, which explains non-obvious data-sourcing behavior not captured in 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?

A single front-loaded sentence with no filler: the action, the source, the input method, and the returned fields all appear in one pass. Every clause earns its place.

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?

An output schema exists so return values needn't be enumerated, and the critical US-coverage constraint is stated. What is missing is how out-of-coverage or ocean coordinates are handled (error vs. nearest fallback), a small gap for an otherwise simple read 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?

Schema description coverage is 100% and both lat/lon already carry format examples and hemisphere guidance, so the schema does the heavy lifting. The description only reinforces the lat/lon input pattern and US-only constraint, adding minimal meaning beyond the structured data. Baseline 3 applies.

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 (get) and resource (latest observed weather conditions) plus the scope (US, by lat/lon) and the data source (nearest NWS observation station). This clearly separates it from weather_forecast and weather_alerts without needing to open either 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?

"Latest observed" and "nearest NWS observation station" frame the usage context well enough to distinguish current conditions from forecast twins, but the description never explicitly names weather_forecast as the alternative or states a when-not condition. Clear context, no explicit exclusions.

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?

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the bar is lower. The description adds genuinely useful behavior beyond them: US-only coverage via NWS, the shape of the response (named periods with temperature, wind, short + detailed forecast), and the existence of a different mode. It does not mention rate limits or data staleness, keeping it out of 5 territory.

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 sentences, zero filler. Purpose and scope come first, the response shape second, and the geocode routing hint last, so the most decision-relevant information is front-loaded.

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 read-only, open-world lookup with a full output schema and 100% parameter coverage, the description supplies everything an agent needs: what it returns, the coverage limitation, and the prerequisite for address-based input. No material gap remains.

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 lat/lon/hourly are fully documented in the schema, establishing the baseline of 3. The description reinforces the lat/lon and US-coverage semantics but adds no format or constraint detail the schema does not already carry, and never mentions the hourly toggle.

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 and resource (multi-day weather forecast), the required inputs (latitude/longitude), and the data source (National Weather Service). The 'multi-day' scope plus the returned named periods distinguish it from weather_current, and it names geocode as the sibling to use for addresses.

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?

Explicitly gives the prerequisite routing rule: 'Use geocode first if you only have an address.' That is clear context plus an alternative. It stops short of stating when to prefer weather_current or weather_alerts, so it is not a full when/when-not/alternatives treatment.

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