Windshield Weather

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

Annotations already cover read-only/idempotent/no-side-effects, so the bar is lower, and the description still adds real behavior: missing or ambiguous places return a clarification, the response includes credits and a drive link, and the output is text plus structured data with no card. It does not state rate limits or failure modes beyond the ambiguity case.

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 tight sentences, front-loaded with the core purpose before the output-shape and sibling details. Slightly dense with multiple facts stacked, but each sentence carries distinct decision-relevant 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?

There is no output schema, so the description carries the return-value burden and does so: text plus structured data, no card, includes data credits and a drive link. Combined with the five-parameter coverage, an agent has everything needed to invoke and interpret it.

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 baseline is 3, but the description adds meaning the schema does not: departure defaults to 'now', planned departures are interpreted as local time at the origin within ten days, and omitted origin falls back to the assistant's shared approximate area. That genuinely clarifies defaulting behavior across parameters.

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 (arrival-time weather along a drive between named places) with a scope qualifier (defaulting to departure now). It explicitly distinguishes itself from the interactive sibling, so an agent can differentiate without opening 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?

Gives clear context for when this tool fits (scheduled or background checks, summaries and comparisons) and names the alternative (get_drive_weather_interactive) plus its differentiator (interactive forecast card). It stops short of steering between this and the highway-weather siblings, so selection among all four is only partly resolved.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavior: the ten-day horizon, local-time interpretation of planned departures, clarification on missing/ambiguous places, and the returned payload (text, structured data, card, credits, link).

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 tight sentences, front-loaded with the core capability and then the differentiating sibling comparison. No filler, though the credits/link detail is secondary and could be trimmed for a shorter front-load.

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 return-value burden and does so: text plus structured data plus an interactive card, along with credits and a deep link. Error behavior (clarification requests) is also stated, making the definition complete for correct invocation.

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 parameters are already fully documented and the baseline is 3. The description restates the 'departure now' default and the ten-day window already present in the schema, adding no new syntax, format, or edge-case detail beyond it.

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?

Opens with a specific verb+resource+scope: 'Arrival-time weather between named places, defaulting to departure now.' It explicitly names the sibling get_drive_weather and states the distinguishing feature (interactive card vs. no card), so an agent can route between the two without opening 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?

It clearly frames when to prefer this variant ('with an interactive forecast card') versus the paired tool ('for background checks'). It does not spell out when to prefer this over the highway weather siblings, so the guidance is clear but not exhaustive.

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 readOnly/idempotent/non-destructive, and the description adds substantial extra context: what time horizons are returned (now, 3, 6, 12, 24 hour), that official road-condition service links are included, that road closures are out of scope, and that output is text plus structured data with no card. This is rich behavioral disclosure beyond the safety hints.

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 tight sentences, front-loaded with the core purpose followed by scope, limitations, and the sibling comparison. Slightly dense, but every sentence carries distinct information and none is padding.

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 by describing the return shape (text and structured data, no card) and the reading windows included. Combined with the annotations and complete schema, an agent has everything needed to call this 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 schema already documents highway and region, and the description largely restates the region scoping ('optionally scoped to a state, province or town') rather than adding new format or syntax guidance. Baseline 3 is appropriate when the schema carries the parameter burden.

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 ('Read the current published forecast for a supported highway') plus the scope modifier. It explicitly names the sibling get_highway_weather_interactive and how the two differ (card vs no card), so an agent can route correctly without opening 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?

Gives positive selection criteria ('suitable for scheduled or background checks and summaries'), an exclusion ('does not report road closures'), and names the alternative tool with the condition that selects it (interactive card). Nothing 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the forecast horizons returned, the inclusion of official road-condition service links, the response shape (text plus structured data with an interactive card), and a negative disclosure about road closures. It stops short of mentioning rate limits or data freshness/auth needs.

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 sentences, front-loaded with the core action, and every sentence carries information (scope, content, exclusion, sibling routing). The clause 'Returns text and structured data with an interactive forecast card' partially restates the title's '(card)' label, which is the only mild 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?

With no output schema, the description carries the burden of describing returns, and it does: text plus structured data with an interactive card, the time horizons, and road-condition links. Combined with the routing to the non-card sibling and the road-closure caveat, an agent has everything needed to select and call 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 description coverage is 100%, so all three parameters are already documented, and the baseline is 3. The description corroborates the 'region' semantics by saying the forecast is 'optionally scoped to a state, province or town', but adds no syntax or format detail beyond the schema and never mentions the 'intent' parameter.

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 ('Read the current published forecast for a supported highway'), names the optional scope, and enumerates the delivered content (now/3/6/12/24h readings, road-condition links). It explicitly distinguishes itself from the sibling get_highway_weather, so an agent can separate the two without opening 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?

Names the alternative tool explicitly and gives the condition that selects it: the paired get_highway_weather returns the same forecast without a card 'for background checks', implying this tool is for card/interactive presentation. It also states a clear exclusion ('This does not report road closures'), so the agent knows what not to rely on it for.

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