kosmos.info.pl

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

Annotations already declare readOnly, idempotent, openWorld=false and non-destructive, so the safety profile is covered. Beyond that, the description adds genuinely useful context: the upstream data source (NOAA Kp index) and the shape of the answer (per-region intensity, Kp thresholds, current Kp, multi-day forecast). It does not address data freshness or caching, which keeps it below 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?

It is a single dense run-on sentence with nested clauses and parenthetical enumerations, which makes it harder to parse than a short front-loaded statement plus supporting detail. Nothing is redundant, but the structure could be split for scanability.

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, full schema coverage and rich annotations, the description only needs to establish scope, data source and output categories, and it does all three. The remaining gap is behaviour with zero arguments (presumably all regions) and forecast horizon, which is not stated.

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?

The description hints at the two location modes ('north, centre and south of Poland or in a given city'), which loosely maps to the city vs lat/lon parameters, but it adds nothing about the lat/lon pairing semantics, the nearest-seat behaviour, or the lang option. With 100% schema description coverage, the schema already carries this load, so 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 concrete verb+resource (aurora visibility in Poland tonight) and its data source (NOAA Kp index), and enumerates the outputs: intensity level per region or city, required Kp, current Kp and a multi-day forecast. This clearly separates it from siblings like planets_tonight or iss_passes, which concern other sky objects.

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 the strong topical framing (tonight's aurora in Poland), but there is no explicit when-to-use/when-not guidance and no sibling is named as an alternative or complement. An agent must infer that this is the tool for aurora questions 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?

Annotations already declare this as read-only, idempotent, non-destructive and closed-world. The description adds useful behavioral context beyond that: it filters to naked-eye-visible passes and limits results to the next 10 days, though it does not discuss permissions, rate limits, or ordering.

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 definition is a single front-loaded sentence with no filler, and the key visibility and timeframe constraints appear early. It is slightly dense because it also lists return fields that the output schema likely covers.

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 forecast tool with rich schema coverage, annotations and an output schema, this description supplies the essential scope, visibility filter, and time horizon. The remaining omissions are mostly explicit sibling routing and default-language behavior, which are handled elsewhere or are minor.

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 lat/lon/city/lang parameters are already well documented, including the nearest-voivodeship-seat fallback. The description confirms the Polish-city scope but adds no parameter syntax or format details beyond the schema.

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 the resource and scope: visible ISS passes over a Polish city during the next 10 days, including per-pass start, peak, end and brightness. It is specific enough to be distinguishable, but it does not explicitly contrast itself with sibling tools such as tonight_sky or planets_tonight.

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 the visibility and 10-day forecast framing, so an agent can infer this is for ISS pass lookups rather than aurora, meteor shower, or planet queries. However, there is no explicit when-to-use versus alternatives guidance or any exclusion criteria.

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 safety (readOnly, idempotent, non-destructive, closed-world), so credit goes to what the text adds: the fixed twelve-month horizon, the Poland-only geographic restriction, Polish-time maxima, an 18-city breakdown, and moon-interference reporting. These are real behavioral constraints an agent would not know from the annotations alone.

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 information-dense sentences with the scope front-loaded and no filler. The second sentence ('With a shower ... only that one, and for the six main ones ...') is slightly elliptical and takes a second read, costing a point but not wasting space.

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, return-format explanation is not required, and annotations carry the safety profile; the description supplies the geographic, temporal, and structural scope that schema and annotations cannot. Nothing essential for a correct call 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 coverage is 100%, so baseline is 3, but the description goes further by explaining the consequence of supplying 'shower' — output narrows to one shower and, for the six main ones, expands to per-city nights. It also seeds example identifiers (perseids, geminids, Leonidy), reinforcing the enum beyond the schema list.

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 resource (the twelve main meteor showers), scope (seen from Poland, next twelve months), and enumerates the returned fields (activity, maximum in Polish time, ZHR, best hours, moon interference). This is clearly distinguishable from siblings like planets_tonight or iss_passes 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?

It implicitly explains the two calling modes — no argument returns all showers, passing a shower returns just that one (with per-city nights for the six main ones) — but it never says when to pick this tool over tonight_sky or other sky-event siblings. Usage is inferable but there is no explicit alternative routing or exclusion.

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 real behavioral detail beyond them: a fixed seven-night horizon, a 10° altitude threshold, dark-sky-only filtering, inclusion of cloud cover, and Warsaw as the fallback location.

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 dense sentence with no filler; the object list leads, the measurement criteria follow, and the default trails at the end. The colon-and-list construction is slightly dense but every clause carries 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 no explanation, and annotations carry the safety profile. The description supplies the horizon, threshold, and default location; the only residual gap is that it does not resolve how lat/lon interact with city, though the schema hints at 'nearest seat'.

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 regardless of description. The one addition is the default-location rule ('Warsaw when no place is given'), which all four parameters being optional makes genuinely useful, but the lat/lon-versus-city precedence and the lang enum are left entirely to the schema.

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 resource (Mercury, Venus, Mars, Jupiter, Saturn) and scope (next seven nights, Polish city, dark hours), plus the specific outputs (rise-above-10° time, highest point, brightness, cloud cover), so an agent knows precisely what it gets back. It never states a verb, but the content is specific enough to distinguish it from aurora_forecast, iss_passes, and meteor_showers; only tonight_sky remains an unaddressed overlap.

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 the content ('over a Polish city for the next seven nights'), and the default 'Warsaw when no place is given' removes one decision point. There is no explicit statement of when to prefer this over the sibling tonight_sky, nor any exclusion, so an agent must infer routing.

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 reveals that the verdict pulls in MET Norway cloud cover, ISS passes, aurora chance, and other external live data. The annotations declare openWorldHint=false, which contradicts that external data sourcing. Because the description contradicts an annotation, this scores 1.

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 dense sentence front-loads the verdict and then lists components with semicolons. It is efficient but slightly run-on; every clause adds 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?

Given the complex aggregate nature and the presence of an output schema, the description covers all major data sources and the default location. It is complete enough for an agent to understand what the tool returns.

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 adds a meaningful default not in the schema: Warsaw when no place is given. The other parameters are fully documented in the schema, so no further compensation is needed.

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 resource — tonight's sky verdict — and enumerates the exact components returned: dark hours, cloud cover, moon, ISS, aurora, planets, and meteor shower. This distinguishes it from the individual sibling tools, which each cover only one of those 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?

It states the context — a Polish city, defaulting to Warsaw — but does not explicitly say when to choose this aggregate verdict over the individual sibling tools like aurora_forecast or iss_passes. The aggregate nature is implied rather than routed.

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