Renovation yield ranking: scan all 16 Nagoya wards to rank neighborhoods by yield. | リノベ利回りランキング。名古屋市全16区の主要町丁目を横断スキャンし利回り上位をランキング。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | 上位何件を返すか | |
| floorArea | No | 想定面積 (㎡) | |
| buildingAge | No | 想定築年数 | |
| propertyType | No | mansion |
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 declare readOnlyHint=true and destructiveHint=false, covering the safety profile, so the bar is lower. The description adds the cross-ward scan behavior ('scan all 16 Nagoya wards'), which is useful contextual information beyond the annotations. It does not disclose return format or pagination limits, but annotation coverage makes 3 appropriate.
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 at two sentences, with the English purpose front-loaded and the Japanese translation after. The bilingual repetition adds minor redundancy but no waste; the core scoping information is delivered efficiently.
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 ranking tool with all 4 parameters optional and annotated as read-only, the description covers scope and purpose adequately. However, it omits details about what constitutes the yield computation, what data types it relies on, and the output shape (no output schema exists). Since an agent could invoke it correctly with defaults, but gets no information about the result format, 3 is fair.
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 75%, and the schema already documents all four parameters (limit, floorArea, buildingAge, propertyType) with descriptions and defaults. The description adds the yield-ranking context that connects floorArea/buildingAge to the yield computation, but provides no parameter-specific syntax beyond the schema. Baseline 3 is correct given high schema coverage.
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+resource: scan all 16 Nagoya wards and rank neighborhoods by renovation yield. It clearly distinguishes from analysis tools like analyze_renovation_yield by establishing a cross-ward scanning scope. However, it doesn't explicitly name sibling differentiators, so a 5 isn't warranted.
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 siblings such as analyze_renovation_yield, discover_opportunities, or detect_arbitrage_signals. The description implies a use case (ranking across all wards) but never states exclusions or alternatives, leaving the agent to infer 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.
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.