Suomiatlas — Finnish area statistics

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

No annotations are present, so the description carries full disclosure burden. It explicitly reveals silent truncation for free callers, the `locked` field reporting dropped areas, and the meaning of null values as suppressed/unpublished rather than zero. This is unusually rich and actionable.

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, each carrying essential information: purpose, input flexibility, truncation behavior, and null interpretation. It is dense but well-structured, with the most critical caveat placed immediately after the purpose.

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 absence of annotations and output schema, the description covers the major operational quirks needed to invoke and interpret results correctly. It does not detail the exact output shape beyond `locked` and nulls, but the provided information is sufficient for selection and 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 coverage is 100% with descriptions for both year and places, giving a baseline of 3. The description goes beyond the schema by explaining the free-tier two-area limit, the `locked` field, and null semantics, which are critical for correct invocation and interpretation.

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 a specific verb and resource ('side-by-side statistics for several Finnish postal areas') and adds differentiators like 'national benchmarks and percentiles' and 'accepts names or codes.' This clearly distinguishes it from siblings such as rank_areas or get_place_stats.

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 use case—comparing multiple Finnish postal areas—is implied by the title and first sentence, but there are no explicit alternatives or when-not-to-use conditions. An agent can infer when to use it, but the description does not provide routing guidance.

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 provided, the description carries the full behavioral burden. It meaningfully discloses that similarity is multi-dimensional, not geographic, and explains that suppressed areas are excluded and absence from results means 'unmeasured' rather than 'dissimilar'. This is valuable behavioral context beyond the name and 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?

The description is compact and front-loaded, stating the core result first, then the use case, then the key caveat about suppressed areas. Every sentence adds value and none is redundant with the schema or title.

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?

The description is complete enough for a 3-parameter tool with full schema coverage and no output schema. It explains purpose, scope, statistical behavior, and an important edge case. It does not describe the return format or whether similarity scores are included, but this is a minor gap given the clarity of the rest.

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 schema already documents all three parameters. The description adds context around what 'place' means and the holistic nature of the comparison, but it does not add concrete parameter-level details such as year behavior or limit semantics beyond what the schema provides. Baseline 3 is appropriate.

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 tool's function: find postal areas most like a given one across a whole statistical profile including income, age, education, housing, and employment. It also explicitly distinguishes itself from single-metric tools and from geographic similarity, which separates it from siblings like rank_areas and compare_areas.

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 gives a concrete use case ('where else in Finland feels like this neighbourhood?') and clarifies that similarity is statistical, not geographic, so results are spread across the country. It does not explicitly name sibling alternatives or state when not to use the tool, so it falls 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?

With no annotations, the description carries the full burden, and it is exemplary: it discloses the annual-mean sampling, WHO/EU comparison, the verdict format, the locked/empty series behavior behind a paywall, and the critical gap reporting rule ('report that as unmeasured, never as clean'). This is far beyond what the schema provides.

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 dense but every clause earns its place: the first sentence defines scope and sources, the second gives the user-facing use case, the third explains access control and locked, and the fourth warns about gap handling. There is no filler and the core purpose is front-loaded.

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?

Despite having no output schema and no annotations, the description covers data sources, benchmark standards, verdict style, paywall implications, the `locked` field, and sparse-coverage gap semantics. For a 2-parameter tool with this complexity, an agent has enough to invoke it correctly and interpret results 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?

The input schema already covers both parameters with 100% description coverage, including the distinction between municipality median and postal-area nearest station for `kind`. The description adds context about series and locked, but that relates to output behavior rather than parameter semantics, so it does not materially raise the baseline.

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 tool's specific verb and resource: measured annual-mean air quality (PM2.5, PM10, NO₂, O₃) for a Finnish postal area or municipality, with WHO/EU benchmark comparison. It also distinguishes itself from siblings by emphasizing a verdict-based answer rather than a bare number, which makes the tool's identity unambiguous.

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 clear context: when you need to answer 'is the air clean in Vantaa?' and it explains the free vs Pro/Area Pass data access split. However, it does not explicitly name sibling tools or state exclusions such as 'use get_place_stats for non-air-quality stats,' so it falls just short of fully explicit alternatives.

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 provided, the description carries the full behavioral disclosure burden. It discloses the key non-obvious behaviors: the tool returns a URL and never the file, the link still comes back without entitlements while the `locked` field indicates cost, and the report renders the same data as other tools. This is substantive and goes beyond a simple 'returns a report' statement.

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 three sentences and front-loads the core purpose before diving into usage caveats. Every sentence serves a distinct purpose: what it returns, when to use it, and the entitlement behavior. It is slightly dense but remains efficient and well-structured.

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 simple link-returning tool with no output schema, the description covers the essential context: what is returned, the report content, the access caveat, and the `locked` field for cost information. It also routes users to the correct sibling tool for data questions, making the description adequately complete for selection and 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 place, year, and language are already fully documented in the schema. The description reinforces that place must be a postal area and not a municipality, but it adds no fundamentally new parameter-level meaning. A baseline of 3 is appropriate.

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 tool returns a download link for a postal area's printable PDF report, explicitly says it returns a URL and never the file itself, and distinguishes it from get_place_stats by pointing out that data questions should go there. This is a specific verb+resource with strong sibling differentiation.

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 gives explicit when-to-use guidance: offer the link when someone wants the document, and answer questions from get_place_stats instead. It also clarifies scope limitations, noting reports exist per postal area only, not per municipality, which helps agents avoid misapplying the tool.

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?

No annotations are provided, so the description carries the behavioral burden, and it does a good job: it explains free-vs-Pro limitations, the 3-year default window, locked fields, and the trendMetrics indicators for postal areas. It does not explicitly state the operation is read-only or describe the exact representation of locked fields, but the most important data-availability caveats are present.

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 front-loaded with a strong purpose statement and every sentence is relevant, but the free-tier explanation is a dense multi-clause run-on, and 'whose latest values are free for everyone' is partly repeated by the following sentence. It is effective but could be tightened without losing meaning.

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 tool with no output schema, the description covers the main return shape (`series`, `trendMetrics`, `locked`) and even handles a likely misinterpretation by warning that a short window is not evidence of a short trend. The main gaps are the lack of an explicit response structure and how the optional `kind` parameter resolves ambiguous place names, but the agent has enough to call the tool 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 coverage is 100%, so the baseline is 3, but the description adds real value beyond the schema. It explains that `variables` defaults to housing prices and population, that postal areas receive extra `trendMetrics`, and that the free tier changes which data is returned — all of which the raw schema does not convey.

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 opens with a specific resource ('one Finnish postal area or municipality') and a clear operation ('Time series ... with direction and size of change computed'). It also answers concrete questions like 'have apartment prices been rising in Espoo?' and 'is the population growing?', which makes the tool's one-place trend-analysis role obvious and distinguishes it from multi-area siblings like compare_areas and rank_areas.

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 gives clear context: use this when you need a time series for a single place and want trend direction/magnitude without eyeballing the data. It does not explicitly name alternatives or state when not to use this tool, so it stops one step short of fully explicit 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?

With no annotations, the description takes on full behavioral disclosure. It explains ambiguous-name handling, locked-field withholding, null suppression semantics, postal-area ratios, and the default-to-headline behavior. This is exemplary transparency for an unannotated 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 information-dense but every sentence contributes: scope, examples, parameter behavior, response fields, and data-disclosure semantics. It is front-loaded with the core purpose and uses examples to ground the tool's intent without unnecessary 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?

Given the absence of an output schema and annotations, the description covers response shape, edge cases, default behavior, and how to customize it. It also explains nuanced data-presentation rules such as locked versus suppressed values. An agent has enough context to invoke the tool and interpret results 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?

The input schema already documents all six parameters, so the baseline is 3. The description adds useful semantic context beyond the schema: variables are fetched from list_variables, the headline set is returned by default, and null/locked values have special meaning. This elevates parameter understanding beyond bare schema descriptions.

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 ('one Finnish postal area or municipality') and a precise action ('current statistics'), then enumerates the metric families it returns. It also gives concrete example queries, which makes it immediately recognizable and distinguishable from historical or comparative sibling tools.

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 makes clear when this tool is appropriate: for current statistics about a single place, by name or code. It also points to list_variables for extra codes and explains the ambiguity fallback. It does not explicitly contrast with get_place_history or get_area_report, but the 'current statistics for one place' framing provides enough contextual guidance.

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 provided, the description carries full responsibility for behavioral disclosure. It explains that results are grouped by theme and include codes, units and types; that passing variableCode switches the response to year coverage; that coverage varies by metric; and that an empty year list means unpublished rather than zero. These are non-obvious semantics an agent could not infer from the 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?

The description is long but every sentence earns its place: primary purpose, directed usage, alternative-mode behavior, an important exclusion, and a subtle edge case. It is front-loaded with the core catalogue purpose before diving into conditional behavior.

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 must compensate by describing what the response contains, which it does. It also covers the two call modes, special air-quality exclusions, and the unpublished-metric sentinel. For a lookup/catalogue tool this is complete enough for an agent to invoke 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 coverage is 100%, so the baseline is 3. The description adds value beyond the schema by elaborating on variableCode: it clarifies that year coverage differs per metric and provides concrete examples plus the important empty-list meaning. It adds less for the group parameter, which the schema already documents well.

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 a specific action and resource: it is the catalogue of every Suomiatlas metric, grouped by theme, with codes, units and types. It clearly distinguishes itself from siblings like rank_areas or get_place_stats by explaining it is the lookup tool for finding variableCode values.

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 explicitly tells the agent when to call it ('Call this to find the right variableCode for rank_areas or get_place_stats') and explains the alternative path for air-quality codes, which should be passed to rank_areas directly rather than looked up here. It also explains the variableCode mode for retrieving years, giving clear conditional guidance.

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, and it does so thoroughly: missing municipalities are 'unmeasured, never as clean or safe', nulls in additionalValues mean unpublished not zero, free callers get at most 10 rows, and 'near'+'withinKm' means straight-line distance. The aq_* order inversion and the 'balance' semantics are also disclosed.

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 long, but it is packed with non-redundant operational facts and each sentence earns its place. Caveats are grouped logically by metric grain, ordering semantics, missing-data interpretation, and multi-metric screening, with the core ranking purpose front-loaded.

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 complex tool with eight parameters, no annotations, no output schema, and several tricky behavioral nuances, the description is nearly exhaustive. It covers metric sources, ordering special cases, missing-data handling, free-tier limits, geographic semantics, and alternative tool routing — nothing essential is left for the agent to guess.

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?

Even though schema coverage is 100%, the description adds substantial semantic value beyond the schema: 'balance' is only valid for gender_balance_20_39, air-quality metrics are municipality-grain and not in list_variables, includeVariables is a single-call screening mechanism, and scope is not applicable for crime/air-quality rankings. These are exactly the non-obvious meanings an agent needs.

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 — 'Rank Finnish postal areas by any metric' — and immediately lists concrete metrics and scoping options. It distinguishes itself from get_air_quality and get_place_stats, so an agent can tell it apart from siblings without opening schemas.

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 guidance is explicit: get_air_quality is for one place only, list_variables supplies valid metric codes, and get_place_stats should not be looped per area to collect a second metric. It also explains when to use includeVariables instead of multiple calls, and when scope is not applicable.

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, and it delivers: optional diacritics, shared-neighbourhood matching producing multiple results, inhabitant counts carrying a publication year, and the crucial fact that null population does not mean an empty place. This goes well beyond a generic search-tool description.

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 front-loaded with the core purpose and each additional sentence earns its place by addressing a realistic ambiguity or data-null pitfall. It is dense but not wasteful, and the progression from purpose to behavior to data semantics is logical.

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 no output schema and no annotations, the description covers the essential context: what kind of input is accepted, what to do with multiple results, and how to interpret population fields. An agent should be able to invoke the tool and interpret its results 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 baseline is 3. The description adds real semantic value by giving concrete query examples (Toukola, Espoo, Uusimaa, 'toolo' finding 'Töölö') and explaining what each kind result means. The limit parameter is already documented in 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 states a specific verb and resource: 'Resolve a Finnish place name to the code every other Suomiatlas tool takes.' It explicitly covers the three kinds of entities handled and positions the tool as a prerequisite for other tools, clearly distinguishing it from 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?

It gives explicit guidance: 'Call this first whenever the user names a place rather than a code.' It also explains what normal ambiguity looks like and instructs the agent to present choices rather than assume the first result, which is actionable usage direction.

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