get_vacancy_statsVacancy rate statistics (空き家率) by municipality: total vacant, for-rent, for-sale, other — compared to national average. | 市区町村別の空き家率・種類別内訳を全国平均と比較して返す。
| Name | Required | Description | Default |
|---|---|---|---|
| area | No | Target city (e.g. '名古屋市中区') — omit for full prefecture | 対象市区町村 | |
| prefecture | No | 都道府県名（和名/英名/ISO 3166-2 コード対応） | 愛知県 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds scoping context (municipality grain, national-average comparison) but does not disclose return format or behavior when data is missing. Consistent with annotations, adds modest value beyond them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact bilingual sentences, key scoping info front-loaded, no filler. The bilingual mirror is slightly redundant but serves the JP-heavy domain, so it earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only, fully-schema-documented, optional-parameter tool with no output schema, the description conveys the result contents (type breakdown + national comparison) sufficiently. An agent can call it correctly; only edge-case behavior is left unspecified.
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% — both parameters carry documented descriptions including the 'omit for full prefecture' nuance on area and the name/ISO-code handling on prefecture. The description adds no parameter syntax on top; 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?
States a specific verb+resource ('vacancy rate statistics by municipality') and enumerates the exact breakdown returned (total vacant, for-rent, for-sale, other) plus the national-average comparison. This clearly distinguishes it from statistics siblings like get_population_outlook and get_real_estate_macro_snapshot.
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 context of use is implied — an agent needing vacancy-rate data by municipality — but the description names no alternatives and gives no exclusions or conditions for choosing this tool over the many statistics/simulation siblings. Adequate but leaves routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools have overlapping purposes (e.g., analyze_renovation_yield vs recommend_renovation_targets, multiple scoring functions). While descriptions provide some differentiation, an agent could easily confuse tools like assess_property_risk, assess_family_friendly_score, and composite_value_score, all of which aggregate multiple axes into a single score.
Most tools follow a verb_noun pattern (analyze_, assess_, get_, simulate_, etc.), but a few deviate with noun phrases (composite_value_score, portfolio_optimizer, scenario_what_if) or adjective-led names (quick_visual_summary). The pattern is largely consistent with minor exceptions, making it predictable overall.
With 33 tools, the surface is quite heavy and exceeds the 25-tool threshold. While the server covers a broad domain (real estate analysis, simulation, contract review, reporting), many tools could be consolidated (e.g., multiple scoring functions). The count feels overwhelming for an agent to manage efficiently, though the scope is comprehensive.
The tool set covers the primary workflows of real estate intel: search/discovery, data retrieval, scoring, simulation, reporting, and contract support. Minor gaps exist (e.g., no direct property transaction listing lookup or lease-specific analysis), but these are not core to the server's stated purpose. The lifecycle of analysis is well-supported.