Ministry of the Environment WBGT heat-stress forecasts for Japan.
Scored across 3 tools
The three tools have mostly distinct roles: hottest ranks stations by next WBGT, wbgt_search filters by location name, and wbgt_sample returns a fixed first-five sample. The main ambiguity is between wbgt_sample and an unfiltered wbgt_search, since both can return a small arbitrary subset.
Two tools share a clear wbgt_ prefix, but hottest is a bare superlative with no prefix or action verb. All names are snake_case and readable, yet the convention is not uniform across the set.
Three tools is reasonable for a narrow WBGT forecast server, with one free sample tool and two PRO access patterns. It is slightly thin, but each tool maps to a recognizable use case.
The surface covers sampling, location search, and hottest-station ranking, but lacks obvious operations such as listing all stations or retrieving a specific station's forecast over time. Agents can work around some gaps via search, but the API feels partial.
PRO. Stations with highest next WBGT value.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) |
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 discloses only a vague ranking criterion and 'PRO' status; it does not explain authentication requirements, rate limits, ordering, forecast horizon for 'next,' or how many stations are returned.
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 very short and front-loaded, with no wasted sentences. However, the two fragments and unexplained 'PRO' make it under-specified rather than optimally concise.
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 annotations and no output schema, the description should explain what 'next WBGT' means, how results are ranked, and how limit affects output. It omits these essentials, leaving the agent with only a high-level ranking hint.
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 50%: access_token is described in the schema, but limit is undocumented in both schema and description. The description does not compensate by explaining what limit controls, its default, or its valid range.
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 identifies a resource ('Stations') and ranking criterion ('highest next WBGT value'), but lacks a clear operation verb such as list or retrieve. It does not distinguish the tool from siblings wbgt_sample or wbgt_search, and 'next WBGT' is ambiguous without further explanation.
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 wbgt_sample or wbgt_search, nor any stated prerequisites or exclusions. 'PRO' hints at a subscription tier but does not tell the agent how or when to select this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
FREE. Heat-stress (WBGT) forecast sample — first 5 stations from MoE Japan.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden; it does disclose the two behavioral facts that matter most — no cost ('FREE') and a hard limit of 5 stations — but says nothing about forecast horizon, update frequency, or return shape. Partial coverage on a zero-param read 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?
One compact sentence that front-loads the cost signal, then the resource, then the scope and source. No 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?
For a no-parameter sample endpoint with no output schema, the description conveys what you get (a WBGT heat-stress forecast) and how much of it (5 stations), which is enough to call it correctly. Only the response format and forecast horizon are 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?
The tool takes zero parameters, so the schema baseline of 4 applies. Nothing in the description contradicts or needs to supplement the empty input object.
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 concrete resource (WBGT heat-stress forecast), a concrete scope (first 5 stations), and the data source (MoE Japan). 'Sample' plus the station cap makes it distinguishable from wbgt_search and hottest, though it doesn't explicitly name those 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?
The leading 'FREE' and the word 'sample' imply this is a low-cost preview to try before using a full/search tool, but no explicit when-to-use or when-to-prefer-wbgt_search guidance is given. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
PRO. Find WBGT rows by prefecture or station name substring (up to 50).
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden and does disclose the searchable fields and 50-row limit. However, it omits return shape, pagination behavior, and permission/auth context beyond what the schema implies.
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 tightly front-loaded with the core action, search fields, and result cap in one sentence. The unexplained 'PRO.' prefix is minor and does not add bulk.
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 two-parameter search tool this is mostly callable, but with no output schema it should say more about what a WBGT row contains and what the response looks like. The absence of annotations also leaves some behavioral details unstated.
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 keyword parameter has no schema description, but the tool description clarifies that it searches prefecture or station name substrings. The access_token parameter is already documented in the schema, so the remaining gap is small.
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 and resource: find WBGT rows by prefecture or station name substring, with a 50-row cap. It is clear what the tool does, though it does not explicitly distinguish itself from siblings hottest and wbgt_sample.
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 search-by-substring purpose implies when to use it, but there is no explicit guidance versus hottest or wbgt_sample. No prerequisites or exclusions are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
hottestwbgt_samplewbgt_searchOfficial JMA short-term forecasts by prefecture.
Nationwide JMA AMeDAS temperature, humidity and precipitation observations.
JMA weather warnings by prefecture.
JMA volcano warnings and eruption forecasts.
Add one secure layer between your agents and this server.