Faceabot Weather

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

Annotations already cover read-only/idempotent/open-world safety, and the description goes well beyond them: data provenance (CAMS Copernicus via Open-Meteo, CC BY 4.0), no API key required, honest disclosure of geographic and seasonal data gaps, and the units/level format returned. These are exactly the facts an agent needs to set user expectations about data availability.

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 capability and coverage constraints, then cleanly labeled "Use when", "Example" and "Data" blocks. The dense parenthetical pollutant lists are information-bearing rather than padding, and every sentence carries either scope, trigger or provenance.

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 no output schema, the description still enumerates the returned quantities and units, notes the forecast horizon, discloses coverage limits, and cites the data source. Nothing material is missing for an agent to call this correctly and interpret the result.

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 location, lat/lon, days and lang are already documented, and the baseline of 3 applies. The description reinforces that days means daily maximums over up to 4 days and supplies a concrete example payload, but it adds nothing about the lat/lon alternative or language handling.

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 (pollen and air quality forecasts) and enumerates exactly what is measured (birch, alder, olive, grass, mugwort, ragweed in grains/m³; European and US AQI, PM2.5, PM10, ozone, NO2). The forecast horizon (now + up to 4 days) and regional scope (air quality worldwide, pollen Europe-only) cleanly separate it from siblings sun_times and weather_forecast.

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?

An explicit "Use when" clause lists concrete triggers (hay fever, allergy, smog, asthma, outdoor sport) plus example phrasings, which is far more than most definitions offer. It also states the important when-not condition for pollen (Europe only, in season). No routing to sibling tools is given, keeping it short of a 5.

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 and openWorld, so the safety profile is covered. The description adds genuinely non-redundant behavior: results are in local time, the lookahead is capped at 7 days, and the tool explicitly reports midnight sun / polar night rather than failing silently. What it omits is how ambiguous or unresolvable locations are handled.

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 output payload is front-loaded, then a compact 'Use when' trigger list, then a single inline example. Every sentence carries information an agent needs and there is no filler.

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?

There is no output schema, so the description carries the burden of describing returns — and it does list the four values plus local-time semantics and the polar edge cases. The only shortfall is the absence of any statement about output shape or the location-versus-coordinates precedence noted above.

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 every parameter and the baseline is 3. The description reinforces the two input modes ('any city or coordinates', 'a date or up to 7 days') but does not resolve the real ambiguity in the schema: 'location' is listed as required while lat/lon are documented as an alternative to it, so an agent still cannot tell whether location may be omitted.

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 names the exact resources returned (sunrise, sunset, solar noon, day length) and the scope (local time, any city or coordinates, one date or a 7-day window). Midnight-sun and polar-night handling further sharpens the boundary against a generic weather sibling. An agent can distinguish this from weather_forecast and pollen_and_air_quality without opening any 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 explicit 'Use when:' block gives concrete trigger queries ('what time is sunrise in Oslo tomorrow?') and use cases (photo, prayer, outdoor planning), which is strong affirmative guidance. It stops short of naming alternatives or exclusions — e.g. no statement that general weather conditions belong to weather_forecast — so it does not reach the top band.

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 read-only, idempotent, open-world, non-destructive behavior, so the bar is lower. The description still adds real context beyond them: the data source and license (MET Norway CC BY 4.0, OpenStreetMap), the fact that no API key is needed, and the 9-day ceiling. It does not discuss rate limits or failure modes when geocoding fails.

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?

Four short blocks with no waste: capability statement first, then 'Use when:', a call example, and provenance/auth info. Front-loaded and easy to scan.

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 no output schema, the description carries the burden of telling the agent what comes back, and it does so by enumerating all returned fields plus the hourly 12-hour block. Combined with the annotations covering the safety profile and the fully documented schema, nothing an agent needs to call this correctly 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 location, lat/lon override, days, lang and units in detail. The description adds only the 'up to 9 days' framing and an example invocation {"location":"Paris","days":3}, which is marginal beyond 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?

The description names a specific verb and resource (current weather + forecast) and bounds the scope precisely: 'up to 9 days', 'any city, address or coordinates worldwide'. Enumerating the returned quantities (temperature, conditions, rain, wind, humidity, UV index, hourly for 12h) makes it unmistakably distinct from the pollen_and_air_quality and sun_times 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?

A dedicated 'Use when:' line gives concrete triggers (weather, forecast, rain, temperature, wind; today/tomorrow/this week). It stops short of explicit exclusions or naming the sibling tools as alternatives for air quality or sunrise/sunset questions, which keeps it below a 5.

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