Ground elevation in metres anywhere in Japan via GSI DEM. Free elevation tool.
Scored across 3 tools
The single-point `elevation` tool is clearly distinct, but `batch_elevation` and `path_profile` both accept up to 50 points and return elevations, differing only in ordering semantics and output framing. The descriptions hint at the difference (ordered path vs. point set), but an agent could easily pick the wrong one for a multi-point query.
All names are lowercase snake_case, with `batch_` and `path_` acting as consistent prefixes on the compound tools. The bare `elevation` for the single-point case is a minor deviation from a strict prefix pattern but remains readable and predictable.
Three tools is at the low end but reasonable for a narrowly scoped elevation-lookup service: one basic lookup, one bulk, one route/path variant. Nothing appears redundant enough to remove, though the surface is thin.
The core domain (querying GSI DEM elevations in Japan) is covered for single points, arbitrary point sets, and ordered paths. Minor gaps exist: no tool to report DEM resolution/coverage bounds or API tier/quota status, so agents must handle out-of-coverage or PRO-limit failures implicitly.
PRO. Elevation for up to 50 lat/lon points.
| Name | Required | Description | Default |
|---|---|---|---|
| points | Yes | ||
| 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 only discloses the 50-point cap; it does not state that the operation is read-only/no side effects, nor does it explain auth/subscriber requirements, rate limits, or error behavior.
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 purpose sentence plus 'PRO.' is front-loaded and low-waste. The unexplained 'PRO.' keeps it from perfect conciseness.
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 read, the schema covers the required points array and token, and the description supplies the batch limit and coordinate type. But with no annotations or output schema, it omits return shape, auth/subscriber context, and sibling routing, leaving clear gaps.
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 50%: points is an untyped array of objects, while access_token is described in the schema. The description adds lat/lon meaning and a max of 50 for points, but does not specify the item object keys or coordinate order, so it only partly compensates.
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?
Names elevation and a batch scope of up to 50 lat/lon points, which distinguishes it from the single-point elevation sibling and path_profile. It lacks an explicit retrieval verb, and the leading 'PRO.' is unexplained.
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 'up to 50 points' limit implies this is the multi-point option, but the description never says when to prefer elevation or path_profile, nor when this tool is inappropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
FREE. Elevation (m) for one lat/lon in Japan via GSI DEM.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | Yes | ||
| lon | Yes |
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 usefully discloses FREE, GSI DEM as the source, meters as the unit, and Japan-only coverage, but omits coordinate reference/order, accuracy, rate limits, and 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 short sentence with no filler; 'FREE.' front-loads useful cost information and the remaining text is dense. The brevity contributes to gaps elsewhere, but as a conciseness measure it is strong.
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 lookup, it covers units, source, and geography. However, with no annotations, no output schema, and 0% schema description coverage, it lacks enough parameter and return context for fully confident 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 0% and there are no per-parameter descriptions. The description only echoes 'lat/lon' and adds no coordinate format, ordering, datum, or bounds for the two required parameters.
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 exactly what is returned (Elevation in meters), for what input (one lat/lon), and the regional/data-source scope (Japan via GSI DEM). The 'one lat/lon' wording also implicitly separates it from the batch and path-oriented 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?
No explicit when-to-use, when-not-to-use, or named alternative is provided. The single-point scope implies it is for one coordinate while batch_elevation handles many, but the agent must infer that routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
PRO. Elevations for up to 50 ordered points (path profile).
| Name | Required | Description | Default |
|---|---|---|---|
| points | 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 full burden, and it only discloses the 50-point cap. It says nothing about the auth requirement (an access_token param exists in the schema), whether excess points are truncated or rejected, or what the response contains for a path (elevation-only vs. distance/gain).
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 terse fragments, no wasted words, but the leading 'PRO.' is an unexplained token that occupies the most prominent position without conveying anything actionable to the 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?
No output schema and no annotations, so the description must explain returns and call behavior; it instead leaves the point object shape, auth flow, and response structure entirely unstated for a 2-parameter geo tool.
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 documented in the schema, while 'points' is an undescribed array of objects. The description partially compensates by stating the points are ordered and capped at 50, but the item shape (lat/lng? elevation refs?) remains undocumented.
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 and shape: elevations for up to 50 ordered points, i.e. a path profile. The word 'ordered' implicitly separates it from batch_elevation and the single-point 'elevation', but the sibling distinction is only implied via the parenthetical 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?
No guidance on when to pick this over batch_elevation or elevation; the agent must infer that 'ordered' points forming a route means path_profile. 'PRO' hints at a paid-tier gate but is never explained, so it functions as noise rather than guidance.
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.
batch_elevationelevationpath_profileLook up elevation worldwide, profile route ascent/descent, grid areas, check terrain line of sight.
Elevation, slope, terrain maps & 3-D surfaces for any site — near-global 30 m, US 10 m, AU/NZ 5 m.
Open-Elevation MCP — terrain elevation by lat/lon (no auth)
Turn coordinates into Japanese municipality names via GSI. Free reverse_geocode tool.
Add one secure layer between your agents and this server.