UK Data: Airport weather (METAR and TAF)

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

Annotations cover safety (readOnly, idempotent, non-destructive), but the description adds behavior well beyond them: chronological ordering, decoded output, a defined summary payload, the 400-report API ceiling (~8 days at half-hourly stations), the 30-day maximum, and a 1-credit cost. That operational envelope is exactly what an agent needs to size a request correctly.

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 statement, then supporting detail in descending priority; every clause (source, cap, exclusion, cost) carries information. It is dense but not padded, though the summary enumeration mid-description is slightly long-winded.

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?

No output schema exists, yet the description explains what comes back: every observation oldest first plus an aggregate summary (high/low temperature, strongest gust, flight-category low, reported weather). Combined with the cap and cost disclosure, an agent can call this correctly without further information.

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 each parameter already documents its type, range, and default, including the note that the summary covers the whole window regardless of limit. The description only restates the hours window ('over the last N hours') and the 30-day bound, adding nothing about interaction between hours and limit. 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+resource+scope: 'Every METAR observation for one airport over the last N hours', plus ordering (oldest first) and a summary payload. The 'what actually happened' framing and the reference to a named upstream source (NOAA/NWS Aviation Weather Center) make the historical-observation role unambiguous against forecast-oriented siblings like taf_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?

Gives a clear when-to-use scenario ('checking what actually happened at a station: rain, gusts, fog, when it cleared') and an explicit exclusion ('not for flight planning'). It does not name the sibling tools it competes with (metar_latest, taf_forecast, pireps_near_airport), so the routing signal is implicit rather than 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?

Beyond the readOnly/idempotent/openWorld annotations, the description discloses the data source (NOAA/NWS Aviation Weather Center, worldwide), a hard freshness constraint ('Only stations that reported in the last 2 hours are returned') that explains missing results, and a per-call credit cost. These are exactly the operational facts an agent cannot infer from annotations or schema.

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-loads the purpose, then the decoded fields, then constraints and cost in a single tight paragraph. The field enumeration is long but functional; a slightly shorter list would lose no routing information, so it falls just short of ideal conciseness.

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?

No output schema exists, and the description compensates fully by enumerating the decoded fields (temperature in C/F, dew point, humidity, wind/gusts, visibility, cloud/ceiling, pressure, flight category). Combined with the source, freshness window, and cost, an agent has everything needed to call it and 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 100% and the schema already documents the ICAO code format, the comma-list limit of 10, and fallback tools for unknown codes. The description only reinforces that multiple airports are supported ('one or more airports') without adding format or limit 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 and resource ('the latest official METAR observation decoded into...') and enumerates the returned quantities, so an agent knows exactly what it gets. It explicitly distinguishes itself from forecast siblings with 'the actual station reading, not a model forecast', separating it from weather, taf_forecast and metar_history.

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 a clear usage context ('what is the weather right now at one or more airports') plus an explicit exclusion ('not for flight planning'), which steers planning queries elsewhere. It does not name the specific alternative tool (e.g. taf_forecast or metar_history) for those cases, so the routing is implied rather than spelled out.

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 establish this is a read-only, idempotent, non-destructive, open-world query, so the description doesn't need to re-state safety. It adds genuinely useful context beyond them: the NOAA/NWS Aviation Weather Center source, US-centric coverage, the sparsity and individuality of reports, and a per-call credit cost.

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 what the tool returns, then the differentiating claim, then source/coverage/limitation/cost in descending priority. Slightly long, but nearly every clause (coverage, sparsity, cost, not-for-flight-planning) carries information the agent would otherwise have to discover empirically.

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?

No output schema exists, yet the description adequately enumerates the returned fields including the severity tally. Combined with annotations and a fully documented schema, an agent has enough to call it correctly; only the sibling-routing detail and pagination behavior are left 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 description coverage is 100%: icao, limit, age_hours and distance_nm all carry types, ranges and defaults in the schema. The description adds nothing about parameter behavior (e.g. how radius interacts with sparsity, or default lookback), 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 resource (PIREPs), a specific spatial scope (within a distance of an airport), and the exact contents returned (turbulence/icing intensity, altitude, aircraft type, time, plus severity tally). The sentence 'PIREPs are the only first-hand reports of turbulence actually encountered' distinguishes it from forecast/model-based siblings such as metar_latest, taf_forecast and 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 a clear use case ('is it bumpy around Denver right now') and an explicit exclusion ('not for flight planning'), plus a coverage caveat ('mainly the United States', 'reports are sparse'). It stops short of naming the alternative tools (METAR/TAF/weather) an agent should pick for flight planning or non-US coverage, so routing is implied rather than 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?

The description adds rich behavioral context beyond the annotations. It details that the forecast is 'decoded into time blocks with plain-English change types (temporary, becoming, 30% chance),' giving the agent insight into the format of the output. It also defines the geographical and data source constraints (NOAA/NWS, worldwide TAF-issuing airports).

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 highly efficient, front-loading the core function while embedding vital operational constraints (airfield only, not for planning) near the end. Every sentence contributes unique value to the agent's decision-making process.

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 its single-parameter input, the description is maximally complete. It covers the data source, the forecast scope, the specific time window (24-30 hours), the output format complexity, and explicit limitations regarding routing and operational use.

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?

Since schema coverage is 100%, the description focuses on reinforcing the necessary context for the 'icao' parameter. It implicitly tells the agent that the provided ICAO must correspond to an airport that officially issues TAFs, adding value to the schema definition.

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 that the tool provides a Terminal Aerodrome Forecast (TAF), which is an official 24-30 hour forecast for specific weather and wind conditions. By defining TAF, it successfully distinguishes its specialized purpose from general weather tools like metar_latest or wind_forecast in the sibling list.

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 provides highly specific guidance by telling the agent what the tool answers ('will it be foggy or windy at the airport tomorrow morning'). Crucially, it also dictates when *not* to use the tool, stating it 'Covers the airfield only, not the route' and 'not for flight planning.'

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