GREENLANDAI

look_through

Read-only

An ordered stack of dated Sentinel-2 stills of one site from t0 to t1, one per window (max_frames, default 6), each with its own scene date. A window with no clear scene is an explicit empty frame, not charged. Agent keys only. Metered: see CHARGING in the server instructions; quote first with billing_quote.

Input Schema

Name	Required	Description
`id`	No	Entity id to anchor on (with entity_type).
`t0`	Yes	Start of the date range, YYYY-MM-DD, on or after 2015-06-23. Required.
`t1`	No	End of the date range, YYYY-MM-DD. Default today.
`lat`	No	Latitude in decimal degrees, -90 to 90 (WGS84).
`lng`	No	Longitude in decimal degrees, -180 to 180 (WGS84).
`max_cloud`	No	Maximum cloud cover of a scene, 0-100 percent. Default 20.
`max_frames`	No	How many equal windows to cut the range into, 1-12; one still per window. Default 6.
`entity_type`	No	Entity kind: deposit \| infrastructure \| company \| project.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedOct 29, 2026
- removedInput schema / properties / entity_type / default
```
Removed value: -null
```
- removedInput schema / properties / entity_type / title
```
Removed value: -"Entity Type"
```
- removedInput schema / properties / id / default
```
Removed value: -null
```
- removedInput schema / properties / id / title
```
Removed value: -"Id"
```
- removedInput schema / properties / lat / default
```
Removed value: -null
```
- removedInput schema / properties / lat / title
```
Removed value: -"Lat"
```
- removedInput schema / properties / lng / default
```
Removed value: -null
```
- removedInput schema / properties / lng / title
```
Removed value: -"Lng"
```
- removedInput schema / properties / max_cloud / title
```
Removed value: -"Max Cloud"
```
- removedInput schema / properties / max_frames / title
```
Removed value: -"Max Frames"
```
- removedInput schema / properties / t0 / title
```
Removed value: -"T0"
```
- removedInput schema / properties / t1 / default
```
Removed value: -null
```
- removedInput schema / properties / t1 / title
```
Removed value: -"T1"
```
- removedInput schema / title
```
Removed value: -"look_throughArguments"
```
- removedOutput schema / title
```
Removed value: -"look_throughDictOutput"
```

Changed1 schema field changedOct 29, 2026

changedInput schema / properties / id / anyOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

Changed8 schema fields changedOct 17, 2026

addedInput schema / properties / entity_type / description

Added value: +"Entity kind: deposit | infrastructure | company | project."

addedInput schema / properties / id / description

Added value: +"Entity id to anchor on (with entity_type)."

addedInput schema / properties / lat / description

Added value: +"Latitude in decimal degrees, -90 to 90 (WGS84)."

addedInput schema / properties / lng / description

Added value: +"Longitude in decimal degrees, -180 to 180 (WGS84)."

addedInput schema / properties / max_cloud / description

Added value: +"Maximum cloud cover of a scene, 0-100 percent. Default 20."

addedInput schema / properties / max_frames / description

Added value: +"How many equal windows to cut the range into, 1-12; one still per window. Default 6."

addedInput schema / properties / t0 / description

Added value: +"Start of the date range, YYYY-MM-DD, on or after 2015-06-23. Required."

addedInput schema / properties / t1 / description

Added value: +"End of the date range, YYYY-MM-DD. Default today."

AddedOct 4, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Goes beyond the readOnly/openWorld annotations by disclosing that empty windows are explicit empty frames and are not charged, that the tool is metered under CHARGING in server instructions, and that agent keys are required. No destructiveness or side effects contradict the read-only annotations; the only gap is that response shape is left to the output schema.

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 what the result is, then constraints, then the billing pointer — four short sentences with little waste. Minor density from jargon such as 'explicit empty frame' and the CHARGING reference, but nothing extraneous.

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?

For a metered, read-only imagery tool with a full schema and an output schema, the description covers the behavior an agent most needs: windowing, empty frames, cost, and auth. The missing piece is sibling comparison, which leaves selection ambiguous among look_at, look_from, and site_reconstruction.

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 description coverage is 100%, so parameter meaning is already fully documented. The description echoes max_frames and its default 6 and clarifies that the range is cut into equal windows with one still each, which is modest added semantics over the schema's own wording.

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

Purpose4/5

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

States a concrete verb and output artifact: an ordered stack of dated Sentinel-2 stills for one site between t0 and t1, one per window. It is distinguishable from a single-image tool only by inference; the sibling tools look_at and look_from are never named, so the boundary between 'look through a range' and 'look at a site/moment' is not made explicit.

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?

The description implies usage through 'quote first with billing_quote' and 'Agent keys only', which gives real preconditions, but it never states when an agent should pick look_through over look_at, look_from, or site_reconstruction. Usage is implied by the window/time-series framing rather than stated.

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

All GREENLANDAI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?