Japan Places — Japan Data Foundry

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

No annotations are provided, so the description carries the full burden, yet it discloses nothing about behavior: not whether it is a read, what it returns, how scores are computed, or any rate/permission constraints.

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 short, but that brevity reflects under-specification rather than conciseness. A single noun phrase cannot front-load useful information for an agent.

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 two undocumented parameters, no annotations, and no output schema, the description is completely inadequate. An agent has no basis to call it correctly or 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?

Two parameters (limit, min_score) exist at 0% schema description coverage, and the description says nothing about either. Notably both are typed as strings, which is counterintuitive for a limit and a score threshold, and the description does not clarify expected formats.

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 is a noun phrase, "街の活気スコア" (city vitality score), which essentially restates the tool name jp_aliveness. It signals the resource (city vitality) but gives no verb, no scope, and no way to distinguish it from siblings like jp_quality or jp_density.

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?

There is no when-to-use guidance, no mention of alternatives among the many jp_* siblings, and no prerequisites or exclusions. The agent is left to guess entirely.

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 supplied, so the description carries the full burden, and it discloses nothing: no data source, update cadence, units, whether the call is a read, whether results are cached or rate-limited, and no indication of return shape. The word 'シグナル' even implies derived/computed output without explaining what that means.

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 short, but shortness here is under-specification rather than conciseness: a single fragment with no lead sentence stating the action or the return. Nothing is front-loaded because there is essentially no content to 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?

For a tool with a required, undocumented identifier parameter, no annotations, and no output schema, the description would need to explain what 'series' accepts and what comes back. It does neither, so an agent cannot reliably invoke this tool from the definition alone.

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 0% and the sole required parameter 'series' is completely unexplained — no format (BOJ series code vs. free-text name), no examples, no valid-value hints. The description does not compensate at all, leaving the agent unable to construct a valid call.

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 phrase '日銀・金融統計・物価指数の時系列シグナル' names the data domain (BOJ / financial statistics / price indices) and hints at time-series signals, which does distinguish it from siblings like jp_crime_statistics or jp_land_price. However, it is a bare noun phrase with no verb, so it never states what the tool actually does with that data (fetch, compute, detect anomalies?). The purpose is only inferable.

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?

There is no guidance on when to use this tool versus the many other jp_* statistics tools, and no mention of prerequisites, data frequency, or coverage period. The agent must guess based on the topic keywords 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?

No annotations are provided, so the description must carry the full behavioral burden, and it discloses nothing: no indication of whether the call is read-only, what geography or station selection is required, whether results are truncated, or what is returned. A bare topical noun phrase leaves the agent with no behavioral information at all.

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 short, but brevity here reflects under-specification rather than efficiency. There is no front-loaded verb or scope statement, so the single line conveys a topic rather than an action.

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 annotations, no output schema, an undocumented parameter, and only a topic label, nothing tells an agent how to construct a call or what to expect back. The definition falls far short of what a one-parameter data tool needs.

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 single parameter 'limit' has 0% schema description coverage and is not mentioned anywhere in the description. Its type is 'string' rather than integer, which makes its meaning (result count? string length? station identifier?) genuinely ambiguous and undocumented in either field.

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 phrase 駅周辺の人口・施設密度 names a resource — population and facility density around stations — but uses no verb, so it is unclear whether the tool fetches a precomputed metric, aggregates data, or performs an analysis. It also fails to distinguish itself from siblings jp_density and jp_facility_signal, which cover overlapping ground.

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?

There is no when-to-use guidance, no preconditions, and no mention of an alternative. With a sibling named jp_density and another named jp_facility_signal, an agent has no stated basis for choosing jp_catchment over them.

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 full burden of behavioral disclosure, and it discloses nothing: no data source, no units, no return shape, no aggregation or ranking behavior, no explanation of what 'density' is measured against (area, population, per-municipality). A five-word fragment is far below what a zero-annotation tool requires.

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 short, but shortness here reflects under-specification rather than conciseness; it is a single fragment with no front-loaded verb, scope, or return statement. Nothing is padded, but nothing useful is conveyed either.

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 two undocumented, oddly-typed parameters, no annotations, and no output schema, the description would need to explain behavior and parameters on its own. It supplies none of that, leaving an agent unable to invoke 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?

Two parameters, limit and min_count, have 0% schema description coverage, and both are typed as strings despite being semantically numeric — a genuine ambiguity the description never addresses. The description does not mention either parameter, so it compensates for none of the coverage gap.

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 'チェーン店の出店密度' names a resource (chain-store location density) but is a bare noun phrase with no verb indicating what the tool actually does — compute, list, rank, or aggregate. It does not differentiate from overlapping siblings such as jp_density, jp_catchment, or jp_facility_signal, so an agent cannot tell which of these density-flavored tools is appropriate.

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?

There is no when-to-use guidance, no mention of alternatives, and no stated preconditions in the description. The only signal an agent has is the phrase itself, which provides no criteria for choosing this over jp_density or jp_catchment.

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 supplied, so the description carries the full burden. It does not disclose the time period covered, whether values are raw counts or normalized rates, the data vintage, or any caveats about the source (総務省統計局 base data). For a statistics tool with zero annotation coverage this is a substantial gap.

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 compact sentence with no filler, and the data source is front-loaded. It is efficient, though brevity here comes at the cost of the missing details noted elsewhere.

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, no annotations, and an undocumented parameter, the description would need to explain return shape, units, and time coverage. It supplies none of these, leaving the agent unable to call the tool confidently.

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 0% for the single required parameter 'prefecture', and the description adds nothing about its expected format — Japanese prefecture name, romaji, or code. With one undocumented parameter the description should compensate but does not.

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 (刑法犯認知件数, penal-code offense counts) and a scope (都道府県別, by prefecture), so the general subject is identifiable. However, the framing as a 'シグナル' (signal) is vague about what is actually returned, and nothing distinguishes it from siblings such as jp_quality or jp_density that also emit prefecture-level indicators.

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?

There is no statement of when to use this tool, when not to, or which sibling to prefer for related prefecture statistics. The agent must infer usage purely from the topic word 'crime'.

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 full burden. It does not state that the tool is read-only, what the data source is, what units 'density' uses, whether results are per-area or per-population, or what the response looks like. Only the bare concept is 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?

It is a single fragment with no wasted words, but it is under-specified rather than concise. There is no front-loaded verb clause or structure to help an agent parse intent.

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 annotations, no output schema, 0% parameter coverage, all-optional parameters, and no usage context, the definition leaves nearly everything an agent needs unresolved. A two-parameter analytical tool needs far more than a four-word label.

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 0%, so both parameters are undocumented in the schema. The description only echoes the parameter names (prefecture, category) without giving accepted values, formats, or behaviour when they are omitted; both are optional, and the description does not explain this.

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 phrase '都道府県×カテゴリのPOI密度' names the resource (POI density) and its two axes (prefecture × category), so an agent can infer what is returned. However, it has no verb and no sentence structure, and it gives no hint about how it differs from density-adjacent siblings such as jp_catchment or jp_facility_signal.

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?

There is no guidance on when to use this tool instead of the many other jp_* tools, no prerequisites, and no exclusions. The phrase implies that density by prefecture and category is its purpose, but nothing tells an agent when this is the right choice.

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 full burden, yet it discloses nothing about whether this is a read or write operation, what the signal looks like, latency, or data freshness. A single tagline is inadequate for a tool with zero annotation coverage.

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 short, but that brevity comes from under-specification rather than efficiency. There is no front-loaded statement of action or scope for the agent to anchor on.

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 annotations, no output schema, and an undocumented required parameter, the definition leaves an agent unable to call the tool correctly. It needs to state the operation, the meaning of 'area', and the shape of the returned signal.

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 0% and the sole required parameter 'area' is completely undocumented. The description does not explain what an area is, its expected format, or valid values, so it fails to compensate for the schema gap.

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 is a tagline ('JEPX electricity supply-demand × weather price signal') rather than a verb+resource statement. It hints at the domain (electricity price) which does distinguish it from siblings like jp_jma_weather, but it never says what the tool actually does or returns.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as jp_jma_weather for weather data. The agent is left to infer everything from the title-like phrase.

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 full behavioral burden. It does disclose data provenance (OpenPOI public-facility category aggregation), which is useful beyond structured fields, but says nothing about whether values are absolute counts or normalized, the time period / snapshot of the data, whether all 47 prefectures are covered, or the response shape for an unknown prefecture.

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 short phrase with no padding, so nothing is wasteful. However, it is under-specified rather than concise: there is no verb, no clause structure, and no front-loaded statement of what the caller gets back.

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 annotations, no output schema, and an undocumented required parameter, the description should carry far more than one noun phrase. An agent cannot confidently construct the call or interpret the result, and the description is written only in Japanese, adding a comprehension barrier for non-Japanese-speaking agents.

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 0% for the single required parameter 'prefecture', and the description never mentions it. The agent is left guessing whether to pass '東京都', 'Tokyo', '13', or a romaji slug — a critical ambiguity for a lookup keyed on prefecture that will silently produce wrong or empty results.

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 metric and source: a prefecture-level public-facility count signal derived from OpenPOI category POI aggregation. That is more than a restatement of the name 'jp_facility_signal', but it is a bare noun phrase with no verb and no indication of what the agent receives (raw counts, normalized index, ranking). It does not distinguish itself from structurally similar siblings such as jp_tourism_signal or jp_density beyond the metric name.

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?

There is no when-to-use guidance, no statement of the question this signal answers, and no named alternative among the 15 siblings. The agent must infer that this is a prefecture-level demographic/infrastructure lookup purely from the word 都道府県別.

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 full burden, and it discloses almost nothing: no statement of read-only safety (only implied by 'search'), no result format, no pagination or rate-limit behavior, and no indication of what a hit contains. The snapshot-count detail is the only real context added.

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 front-loaded phrase with no wasted words, but the brevity comes from under-specification rather than tight writing. A sentence or two more on query fields and result shape would earn 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?

With no annotations, no output schema, no parameter descriptions, and three parameters including an ambiguously typed 'limit', the definition is not complete enough for confident invocation. The agent cannot predict the response shape or how to page through 26,249 records.

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 0% and all three parameters (q, limit, prefecture) are bare, yet the description compensates for none of them. 'limit' is typed as a string with no format hint, and 'prefecture' gets no indication of accepted values or language, which is a real risk given the Japanese dataset.

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 (search over the gBizINFO corporate registry snapshot) and even quantifies the corpus at 26,249 corporations, so the agent knows what data is behind the tool. However it never says which fields 'q' matches (company name, corporate number, address?) or how this differs from siblings like jp_chains or jp_municipality, so differentiation is left to inference.

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?

There is no when-to-use guidance, no exclusions, and no mention of the alternative tools in the sibling list. The agent must guess whether corporate lookups belong here rather than in jp_chains or jp_quality.

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 full burden, yet it discloses nothing about behavior: not whether it is a read or write, not whether it requires auth, not what an "alert" means (computed list? threshold check?), and not what is returned. This is a complete gap for a tool with zero annotation coverage.

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 short, but brevity here is under-specification rather than conciseness: a single noun phrase with no front-loaded verb, no scope, and no actionable detail. Nothing is wasted because almost nothing is said.

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 four-parameter tool with no annotations, no output schema, and no parameter documentation, the description should explain purpose, filtering semantics, and return shape. It supplies none of these, leaving the definition unusable without opening the schema and guessing.

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?

Four parameters (limit, status, industry, prefecture) exist with 0% schema description coverage, and the description adds no meaning for any of them. It does not say what values status accepts, whether limit is a count or a date, or how industry/prefecture are formatted.

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 is a bare noun phrase, "補助金締切・要件アラート", that essentially restates the tool name (grant deadline alert) with the minor addition of "要件" (requirements). It names a resource but supplies no verb and no scope, so an agent cannot tell what the tool actually returns or does with it.

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?

There is no when-to-use guidance, no mention of alternatives among the many jp_* siblings (e.g. jp_subsidy_award_rate, jp_gbizinfo_search), and no exclusions or prerequisites. The agent is left to guess entirely.

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 supplied, so the description carries the full behavioral burden, and it discloses almost nothing: no time period covered, no units, no observation vs forecast distinction, no pagination or response shape, no auth or rate-limit notes. The only behavioral content is the implicit claim that results are per-prefecture and cover three weather metrics.

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 one short phrase with zero padding, so there is nothing to trim. The trade-off is that the brevity comes from omission rather than compression: it is structured as a label rather than as a front-loaded statement of action and scope.

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 is the only documentation an agent has, and it is insufficient for a data-retrieval tool: the time range, aggregation window, and return structure are all unknown. A caller could invoke it but could not predict or validate the result.

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 0% for the single required parameter, so the description must compensate. The phrase 都道府県別 does confirm the parameter's role as a prefecture scope, which is the minimum needed to use it. But it gives no expected format — Japanese name, romanized name, or JIS code — leaving a real risk of an invalid call.

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 data source (気象庁 / JMA) and the resources covered (気温・降水量・日照時間) at prefecture granularity, so an agent can guess it retrieves weather data. However it is a bare noun phrase with no verb, and the term シグナル ("signal") is undefined, so what the tool actually does with that data (fetch raw observations, compute an index, return an alert) is left to inference rather than stated.

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?

There is no when-to-use guidance, no exclusions, and no reference to any alternative. The sibling list contains several other 'signal' tools (jp_tourism_signal, jp_facility_signal, jp_energy_price) but nothing in the description says how to choose between them or when this one is the right call.

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 full burden, and it discloses only that the data originates from 地価公示. It says nothing about whether the result is a single prefecture-wide average or a list of points, what unit or year the price reflects, rate limits, or whether the call is read-only.

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 single parenthetical phrase is tight and front-loaded with the resource, but it is under-specified rather than genuinely concise. Nothing is wasted, yet almost everything an agent needs is absent.

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 one-parameter read tool with no output schema and no annotations, the description is minimal but not hopeless: the resource and source are identifiable. However, missing code format, unit, and output shape leaves real gaps for an agent to trip over.

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 0% and the single parameter 'prefecture_code' is an untyped-format string with no enum or pattern. The description only implies that the parameter identifies a prefecture; it never states whether the expected value is a JIS code like '13', a name like 'Tokyo', or '東京都' — the most likely source of a failed call.

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 and aggregation ('average land price by prefecture') plus the provenance (National Land Numerical Information, Land Price Public Notice), so the agent knows exactly what data comes back. It does not differentiate from any sibling, though no sibling in the list covers land prices, so confusion risk is low.

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?

There is no guidance on when to use this tool, no prerequisites, and no mention of alternatives among the sixteen jp_* siblings. The agent must infer that this is the land-price lookup purely from the name.

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, and it only discloses the metric categories in the result. It is silent on whether the call is read-only, whether it returns all municipalities in a prefecture or a single municipality, whether values are per-year or per-capita, and what the response shape looks like.

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?

One short parenthetical phrase — there is no wasted wording, but the terseness is under-specification rather than economy. The metric list is front-loaded and useful; everything else an agent needs is absent.

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 one-parameter read tool, the description is complete enough that an agent knows it is a census lookup by municipality. But with zero annotation coverage, no output schema and an undocumented parameter, the description leaves key call-shaping details unresolved.

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 0% for the single required parameter 'prefecture', so the description must explain it, and it does not mention the parameter at all. The phrase '市区町村別' only hints at municipal granularity without clarifying whether the prefecture value filters, expands, or is required.

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 Japanese phrase names the resource ('市区町村別センサス', municipality-level census) and lists the metrics returned (population, corporation counts, POI counts), so an agent can infer it retrieves municipal statistics. However, there is no verb and nothing that separates it from adjacent siblings such as jp_density, jp_catchment or jp_quality, which plausibly cover overlapping geographic data.

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 no when-to-use guidance whatsoever: no indication of when this census beats jp_density or jp_catchment, no preconditions, no mention that data is scoped to Japan or to a single prefecture. Usage must be guessed entirely from the name.

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 bears the full burden and discloses almost nothing: it does not confirm read-only behavior, describe the response shape (buckets, scores, counts), or note any scope limits such as geography or data source. The word 'distribution' weakly implies an aggregate read, which is the only behavioral hint available.

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?

At six words it is maximally compact and front-loaded with the resource, with no filler. The brevity is under-specification rather than efficient concision, so it earns only a middling score.

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 one-parameter read tool this could be simple, but with no annotations, no output schema, and an unexplained min_score, an agent has nothing to reason from beyond the topic. It is not sufficient to invoke the tool confidently.

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 single optional parameter min_score is undocumented in both schema (0% coverage) and description, and its string type is unusual for something named like a numeric threshold. An agent cannot tell whether it accepts a number as text, a bucket label, or a comparison expression, so the description does not compensate for the coverage gap at all.

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 fragment 'ジオコーディング品質の分布' (geocoding quality distribution) narrows an ambiguous name (jp_quality) to a specific resource and implies a statistical/aggregate output, which is real information the name alone does not carry. However, it is a bare noun phrase with no verb, so it never states what the tool actually does — computes, lists, or summarizes — leaving the operation to inference.

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?

There is no when-to-use guidance, no stated alternative among the many jp_* data siblings, and no indication of the scenario this distribution serves. The only implicit signal is that it is a quality/statistics lookup rather than a per-record query.

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 full burden of behavioral disclosure, and it discloses nothing. It does not say whether the result is a computed estimate, a stored statistic, or a lookup; whether the rate is historical or projected; what the confidence or data source is; or what the response contains.

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 short, but the brevity reflects under-specification rather than economy; a single label with no sentence structure and no front-loaded statement of action or scope. Nothing is wasted because almost nothing is said.

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 zero annotations, no output schema, and two undocumented required parameters, the description would need to carry nearly all context. It provides none, leaving an agent unable to invoke the tool correctly or interpret its output.

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 0% and both parameters (industry, prefecture) are required strings with no enum, format, or example. The description adds no meaning at all — it never mentions industry or prefecture, nor acceptable values (e.g. Japanese prefecture names vs. codes, industry taxonomy).

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 is a bare noun phrase, '補助金採択率推定インデックス' (subsidy adoption rate estimation index), which essentially restates the tool name jp_subsidy_award_rate. It signals the resource domain but supplies no verb describing what the tool actually does (compute? look up? list?) and does nothing to distinguish it from siblings such as jp_grant_deadline_alert or jp_gbizinfo_search.

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?

There is no guidance on when to use this tool, when not to, or which sibling to prefer for grant-related questions. An agent has no basis for choosing between this and jp_grant_deadline_alert or jp_gbizinfo_search.

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 full behavioral burden, yet it says nothing about what is returned, the unit of measure (raw person-nights vs an index), the time period or data freshness, or whether a missing prefecture errors. The word 'シグナル' in the name hints at a derived signal but is never explained, leaving the agent guessing about the response shape.

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 compact phrase with no filler, front-loading the source and then the metric. It is terse to the point of being a bare noun phrase, but nothing is wasted.

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 annotations, no output schema, and an undocumented sole parameter, the description should do far more for a data-retrieval tool. It never establishes units, time coverage, or the format expected for 'prefecture', which are exactly the gaps structured fields do not fill here.

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?

There is one required parameter (prefecture) with 0% schema description coverage, and the description does not define its accepted format — Japanese prefecture name, romaji, or a code. The phrase '都道府県別' only confirms that the value selects a prefecture, which the parameter name already tells the agent.

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 metric (外国人延べ宿泊者数, total overnight stays by foreign visitors) at a specific granularity (都道府県別) and a named source (総務省統計局 都道府県データ基礎データ). That is a clear verb-less but unambiguous resource statement. It does not differentiate itself from siblings such as jp_facility_signal or jp_quality, which share the vague 'signal' suffix.

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?

There is no statement of when to use this tool versus the many jp_* siblings, and no indication of what question it answers (tourism demand? inbound trend?). The only implied usage comes from the metric name itself.

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