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

With no annotations, the description carries the full behavioral burden. It discloses the default location source (caller's area) and horizon semantics, which is useful, but says nothing about read-only nature, response size/format, or behavior when geolocation 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?

Two compact sentences, front-loaded with the resource and scope, followed immediately by the horizon mapping. Every clause carries information; nothing is 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?

For a 6-parameter read tool with no annotations and no output schema, the description covers the horizon and location dimensions well but omits any indication of what the response looks like or what happens with the PSI region/haze-related fields. Adequate but with a clear gap around return values.

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 is 3, but the description genuinely enriches the horizon parameter beyond the schema's terse 'Forecast horizon. Default 24h.' by explaining what each value returns (area nowcast vs general/regional periods vs island-wide outlook).

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: 'NEA forecast for the caller's area/region', which tells the agent exactly what it returns and whose location it uses. It doesn't explicitly distinguish itself from siblings like weather_now or get_rain, so sibling differentiation is left implicit.

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 names the three horizon values and marks 24h as the default, which implies the choice depends on the lookahead needed. But it never says when to prefer this over weather_now or get_rain, and gives 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?

With no annotations, the description carries the full burden. It usefully discloses provenance (NEA via data.gov.sg) and freshness ('refreshed hourly'), plus the fact that all five regions are returned. It omits any auth requirements, failure behavior when geolocation or IP lookup fails, and defaults beyond what the schema states.

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, with the scope (nearest PSI region) front-loaded and provenance/freshness trailing. 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?

There is no output schema, so the description correctly enumerates the returned values (24-hr PSI, 1-hr PM2.5, 24-hr PM2.5/PM10, band, advisory, all five regions). No annotations exist, so more on permissions or geolocation fallback would close the remaining gap, but for a read-only atmospheric data lookup this is close to complete.

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 ip, lat, lon, lang, and region with enums and defaults. The description adds nothing parameter-specific, which matches the baseline 3 when structured fields do 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?

The description names a specific verb+resource ('Current haze for the caller's nearest PSI region') and enumerates the returned metrics, so the tool's function is unambiguous. It never names or contrasts against siblings (weather_now, get_rain, get_forecast, locate_me), which is the only thing separating it from a 5.

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 by 'current haze for the caller's nearest PSI region' but there is no explicit when-to-use, when-not, or alternative routing (e.g., vs weather_now or locate_me for geolocation). An agent must infer the context from the purpose statement alone.

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 the disclosure burden and does well: it reveals the geolocation-by-nearest-stations method, the forecast blending, and the island-wide wet-station count. It omits auth/rate-limit facts, but the methodological transparency is a real value-add.

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 answers the core question first and then layers sources; no filler, nothing redundant.

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 and no annotations, yet the description conveys what the call yields (local rain status, forecast, island-wide count) and how it locates the caller. That covers the essentials for calling it correctly, with only return-format specifics left unstated.

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 all five parameters are already documented in the schema, including the lat/lon, lang, and region semantics. The description adds no parameter guidance beyond that, 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?

Answering 'Is it raining near the caller?' plus naming the exact data sources (NEA 5-minute rain-gauge network, nearest three stations, 2-hour area forecast) gives a precise verb+resource. This clearly separates it from get_forecast, get_haze, and weather_now.

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 current-condition usage but never states when to pick this over get_forecast or weather_now, nor any exclusions. Sibling routing is left to inference.

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 the burden but only provides a moderate amount: it discloses the default behavior (public IP) and that it also resolves to an NEA PSI region. It doesn't mention latency, whether it makes network calls, error handling, or what happens if geolocation fails. 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?

Two sentences, front-loaded with the core action and then the rationale. No waste, though it could be slightly tighter. Every sentence 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?

For a 4-param, no-annotation, no-output-schema tool, the description gives a basic overview but leaves gaps: it doesn't explain what the return value looks like (coordinates + region name?), nor does it cover error cases or how the ip/lat/lon overrides interact. It's minimally sufficient but not complete.

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 fully documents every parameter (ip, lat, lon, lang) including defaults and enums. The description adds little beyond reiterating the default IP lookup. Baseline 3 is appropriate when 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?

States a specific verb+resource: resolve the caller's location (public IP by default) into coordinates and the nearest NEA PSI region. This clearly distinguishes it from the sibling weather tools (weather_now, get_haze, etc.) by framing it as the geolocation resolver.

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: "Useful to check what the other tools will use before calling them." This tells the agent when to reach for it (as a prelude to other tools). However, it doesn't name specific alternatives or state when not to use it.

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 the full behavioral burden. It usefully discloses location resolution defaults and overrides, plus the inclusion of NEA health advisory data. But it omits rate limits, data freshness, caching behavior, error handling, and output format expectations, leaving meaningful gaps for a five-parameter 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 with no filler, front-loading the core summary and outputs. The second sentence efficiently covers the location-resolution fallback logic.

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 and no annotations, the description must carry the context, and it does well: it enumerates the returned data (PSI, PM2.5, advisory, rain, forecast) and explains location sourcing. It could be slightly more complete by noting the effect of the lang parameter on labels and health advice, but overall it is strong for this complexity.

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 per-parameter descriptions already do most of the work, establishing a baseline of 3. The description adds integrative precedence semantics: 'Location comes from the caller's public IP unless region / lat+lon / ip is given,' which clarifies how the optional location parameters interact beyond their individual schema docs.

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 states specific data returned: 24-hr PSI, 1-hr PM2.5, NEA health advisory, nearby rain, and 2-hour forecast. It clearly identifies itself as a one-call aggregate for Singapore, distinguishing it from sibling tools like get_haze, get_rain, and get_forecast that provide individual components.

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 phrase 'One-call summary' implies this tool is a convenience aggregator, suggesting when it is useful over separate calls. However, there is no explicit guidance on when to prefer this over get_haze, get_rain, get_forecast, or locate_me, and no exclusions are stated. Usage is therefore implied rather than clearly specified.

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