Convert a CSV/spreadsheet with lat/lon (or X/Y) columns to GeoJSON — auto-detects the coordinate columns (e.g. "map this spreadsheet", "CSV with lat/lon to GeoJSON", "turn my Excel export into map points"). Returns a GeoJSON FeatureCollection as a JSON string.
| Name | Required | Description | Default |
|---|---|---|---|
| csv | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses that coordinate columns are auto-detected and that the output is a GeoJSON FeatureCollection as a JSON string. It does not cover edge cases or error behavior, but for a simple conversion tool the key behaviors are communicated.
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 opens with the core purpose and includes several user-phrase examples that help with intent matching. It is slightly long but every part contributes value, so it remains well-structured.
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?
Given the low complexity (one parameter and an output schema), the description covers the essential purpose, input expectations, and return type. The only significant gap is input format clarity, which is already captured in parameter semantics.
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 schema has one required 'csv' string parameter with 0% description coverage, and the description does not clarify whether the value should be raw CSV content, a file path, or a URL. It only implies the data should contain lat/lon or X/Y columns, which is not enough to fully resolve parameter semantics.
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 clearly states the tool converts a CSV/spreadsheet with lat/lon or X/Y columns to GeoJSON, and explicitly mentions auto-detection of coordinate columns. This distinguishes it from sibling converters like geojson_to_csv, gpx_to_geojson, or kml_to_geojson.
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 description provides clear context through user-intent examples like 'map this spreadsheet' and 'turn my Excel export into map points', which help an agent decide when to use this tool. It does not explicitly mention alternatives or when-not-to-use, but the context is sufficient for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many assess_* composite tools (datacenter, ev_charging, renewable, telecom, due_diligence) share the same building blocks of grid proximity, land cover, and terrain, making their boundaries fuzzy. assess_property_hazard_x402 also duplicates assess_property_hazard with only a payment-method difference, and bundle_* tools intentionally overlap with the free primitives they replace.
There is a mix of verb_noun tools (query_features, geocode_address), noun-first geometry tools (centroids_geojson, envelope_geojson), and inconsistent _geojson suffix usage (buffer_geojson, fix_geometry, geometry_stats). The assess_* and bundle_* prefixes offer some grouping, but no single naming pattern is followed across the set.
With 85 tools, the surface is extreme for an MCP server and far exceeds the typical well-scoped 3-15 range. Many tools are convenience bundles or variants that could be consolidated, making the count a significant usability burden.
The toolkit covers a broad range of GIS tasks: format conversions, GeoJSON analysis, FeatureServer query/inspection, geocoding, site assessment, and sharing. Minor gaps exist (e.g., no Excel-to-GeoJSON, no FeatureServer update/delete), but most missing functionality can be worked around by chaining existing tools.