Skip to main content
Glama

Sentinelhub Ndvi Stats

sentinelhub_ndvi_stats
Read-onlyIdempotent

NDVI vegetation statistics over an area and time range, returns per-interval mean/min/max/stdev of the vegetation index (NDVI) from Sentinel-2 imagery for a bbox or GeoJSON polygon. Derived numbers only, no imagery. Example: sentinelhub_ndvi_stats({ bbox: [12.44, 41.87, 12.53, 41.93], date_from: "2023-05-01", date_to: "2023-09-01", aggregation: "P1M", _apiKey: "client_id:client_secret" })

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "bbox": [
        12.44,
        41.87,
        12.53,
        41.93
      ],
      "_apiKey": "your-sentinel-hub-api-key",
      "date_to": "2023-09-01",
      "date_from": "2023-05-01",
      "aggregation": "P1M"
    },
    "name": "sentinelhub_ndvi_stats"
  }
}

Input Schema

NameRequiredDescriptionDefault
bboxNoBounding box [minLon, minLat, maxLon, maxLat] in EPSG:4326. Provide this OR `geometry`.
_apiKeyYesSentinel Hub OAuth credentials as "client_id:client_secret" (from sentinel-hub.com or free at dataspace.copernicus.eu).
date_toYesEnd date, YYYY-MM-DD.
geometryNoA GeoJSON Polygon geometry (EPSG:4326) as an alternative to `bbox`.
date_fromYesStart date, YYYY-MM-DD.
aggregationNoISO-8601 aggregation interval (default "P1M" = monthly). E.g. "P1D", "P10D", "P1M".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuine context beyond that: the result is computed statistics rather than imagery, the aggregation is per-interval, and a credential format is needed. It stops short of disclosing failure modes such as no-data windows, cloud masking, or quota behavior for Sentinel Hub.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and return shape, then a concrete example – minimal waste. The example is somewhat long and repeats values already visible in the schema examples, which keeps it just short of a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly carries the burden of explaining returns (per-interval mean/min/max/stdev) and the aggregation granularity, which is what an agent needs to consume results. It is silent on response key names and error/no-coverage handling, so it is not fully complete, but for a read-only stats tool it is close.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents bbox ordering, date format, GeoJSON geometry, the ISO-8601 aggregation default, and the _apiKey format, so the description cannot add much. The embedded example shows a complete valid call, which is mildly helpful for assembling arguments but largely restates structured data. Baseline 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('NDVI vegetation statistics over an area and time range') and pins down the payload: 'per-interval mean/min/max/stdev of the vegetation index (NDVI) from Sentinel-2 imagery for a bbox or GeoJSON polygon.' The clause 'Derived numbers only, no imagery' cleanly separates it from a sibling like sentinelhub_catalog_search, which deals in imagery.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the worked example and the 'derived numbers only, no imagery' scoping note, so an agent can infer this is the tool for numeric NDVI time series. However, it never states when to prefer this over alternatives (e.g., catalog search when raw scenes are needed), nor any prerequisites beyond the API key, leaving routing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.