eo-mcp

Overview Schema Source Related Servers Discussions Admin

analyze_coastal_erosion

Quantify coastal shoreline retreat and erosion rates (m/year) between two dates using satellite imagery and automated transects, with no configuration or credentials required.

Instructions

Quantify coastal shoreline retreat and erosion rates (m/year) between two observation dates using automated MNDWI waterlines and DSAS baseline transects conforming to USGS DSAS and EU Climate Adaptation standards. Zero-config: Multi-temporal analysis on open Sentinel-2 archives. No credentials or API keys required.

Args: bbox: Bounding box [min_lon, min_lat, max_lon, max_lat] in WGS84. historical_date_range: Baseline date range (e.g. '2019-05-01/2019-08-31'). recent_date_range: Comparison modern date range (e.g. '2024-05-01/2024-08-31'). transect_sample_step: Interval in pixels between perpendicular cross-shore transects (default 5). collection: Satellite collection name ('sentinel-2-l2a' or 'landsat-c2-l2'). format: Output format ('summary', 'geojson', or 'csv').

Returns: JSON or formatted string with transect measurements, End Point Rate (m/year), hazard classification, and eroding coastline percentage.

References:

Xu, H. (2006). International Journal of Remote Sensing, 27(14), 3025-3033. DOI: 10.1080/01431160600589179
Otsu, N. (1979). IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62-66. DOI: 10.1109/TSMC.1979.4310076
Thieler, E. R., et al. (2009). USGS Open-File Report 2008-1278. DOI: 10.3133/ofr20081278
Vos, K., et al. (2019). Environmental Modelling & Software, 122, 104528. DOI: 10.1016/j.envsoft.2019.104528

Input Schema

TableJSON Schema

Name	Required	Default
`bbox`	Yes
`format`	No	summary
`collection`	No	sentinel-2-l2a
`recent_date_range`	Yes
`transect_sample_step`	No
`historical_date_range`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 23, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the disclosure burden and does so well: it states that no credentials are needed, identifies the automated processing methods, and lists the returned measurements and classifications. It stops short of discussing failure modes or operational constraints, though none are obviously critical for this analysis tool.

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?

The description is well structured with a clear lead sentence, an Args block, a Returns block, and references. The references add scientific authority but are the least actionable part for an agent; overall the length is reasonable for the tool's complexity.

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

Completeness5/5

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

For a six-parameter tool with no schema-level descriptions, the description supplies everything needed to invoke it: argument semantics, examples, defaults, output content, and authentication status. The presence of an output schema further reduces the need to document return structure, and nothing required for a correct call is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description is the only source of parameter meaning; it fully compensates by documenting all six parameters, including bbox order and CRS, date-range format examples, transect step units, collection options, and output formats. This is exactly the value the schema lacks.

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?

The description opens with a specific action and object: 'Quantify coastal shoreline retreat and erosion rates (m/year) between two observation dates', and reinforces it with the method (MNDWI waterlines, DSAS transects). This is clearly distinct from sibling tools like simulate_sea_level_rise or detect_water_sar, and the pair of date ranges anchors the exact workflow.

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

Usage Guidelines4/5

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

It gives a clear applicable context: multi-temporal analysis on open Sentinel-2 archives, zero-config, no credentials required, and a before/after date-range scenario. It does not explicitly state when not to use it or name alternative tools, so it falls short of a full routing guide.

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