Skip to main content
Glama

Aquedra Run

Convert geospatial file

convert_geo_file

Converts a geospatial file (CSV, KML, GPX, GeoJSON or a zipped Shapefile as base64 text) to GeoJSON, KML or CSV and returns the converted text with the feature count. To reproject or measure features that are already GeoJSON use reproject_geojson or measure_geojson. Takes text content up to 1 MiB, or a Shapefile zip of up to about 750 KB, within 1 MiB of arguments and up to 50,000 features and 200,000 vertices. Costs US$0.01 per file from prepaid credits; with the default 3 s it is charged only when it succeeds, and invalid input is never charged. Set dry_run to true to get the price without charging and max_cost_usd to refuse a call that would cost more; for heavier inputs set max_seconds from 4 to 30, where each second over the 3 included costs US$0.0005, the full time is held up front and the unused part refunded, and the price and the time used are charged if the call runs out of time or memory, or is cancelled while running.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "input_format": "<input_format>",
      "content": "<content>",
      "output_format": "<output_format>"
    },
    "name": "convert_geo_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
contentYesThe file content as text. Size limits: csv 1 MiB (at most 200 columns, 50,000 rows and 200,000 cells), kml 1 MiB, gpx 1 MiB, geojson 1 MiB. For shapefile, a base64-encoded .zip (a bare .shp is not accepted) of up to ~750 KB (the whole request must fit in 1 MiB), which may expand to at most 8 MiB of .shp/.dbf/.prj/.cpg parts. csv and kml output accept at most 200 distinct property keys; csv output at most 200,000 cells (features x keys), kml output at most 20,000 features and 80,000 cells.
dry_runNoWhen true, return the price (cost_usd) and units of this call without running it or charging anything.
x_fieldNoCSV only: name of the longitude (x) column. Detected automatically when omitted.
y_fieldNoCSV only: name of the latitude (y) column. Detected automatically when omitted.
max_secondsNoCompute time limit in seconds, 1 to 30 (default 3; 1 to 3 all use the standard 3 s). The price includes 3 s of compute. From 4 to 30 (extended time) the call runs on a separate lane, where buffer accepts larger inputs, and each second over 3 costs the geo_compute_second price: the price plus all those seconds is held at the start (that is what dry_run reports and max_cost_usd is compared with), the seconds not used are refunded, and the response adds compute_ms and max_seconds. With extended time the price and the time used are charged if the call runs out of time or memory, or is cancelled while running: 422 operation_too_complex keeps the whole hold, 422 operation_too_large or 413 result_too_large (a result over 8 MiB) or 499 cancelled keep the price and the seconds used, and those errors carry cost_usd. Any other failure is refunded in full.
input_formatYesFormat of `content`.
max_cost_usdNoThe most this call may cost, in USD, as a number or decimal text with at most 6 decimals (e.g. 0.01 or "0.01"). A call that would cost more is refused with 402 max_cost_exceeded and nothing is charged.
output_formatYesFormat to convert to.

Output Schema

NameRequiredDescriptionDefault
unitsYesPrice units the input measured.
resultNoThe operation's result; absent with dry_run.
call_idNoServer-issued id of the call; absent with dry_run.
dry_runNoTrue when nothing was run or charged.
cost_usdYesWhat the call cost (or would cost, with dry_run), US dollars as decimal text.
compute_msNoExtended time only: the compute time the call was billed on, in milliseconds.
balance_usdNoCredit balance after the charge, US dollars as decimal text; absent with dry_run.
max_secondsNoExtended time only: the max_seconds the call ran (or would run) with.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false; the description goes far beyond that with the cost model, credit charging, refund versus keep-charge rules per error code, and the extended-time lane behavior. The main gap is that it does not restate the write/side-effect profile the annotations imply (credits spent, non-idempotent charging), though the cost paragraph effectively covers it. Very high transparency overall.

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

Conciseness5/5

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

Front-loaded with the one-line purpose and return value, then sibling routing, then limits, then pricing, then optional knobs — a sensible priority order for an agent deciding whether to call. Despite its length, every block is load-bearing (limits, cost, refund policy), and there is no filler or marketing language.

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 paid conversion tool with 8 parameters, it covers input size limits, feature/vertex caps, cost and refund behavior, dry-run pricing, and timeout semantics — everything an agent needs to call it safely. Return values are covered by the output schema plus the stated "converted text with the feature count".

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 every parameter already carries its own documentation, including size limits and the max_seconds hold/refund semantics. The description adds only a compact restatement of max_seconds tiers and dry_run/max_cost_usd purpose, which duplicates rather than extends the schema. Baseline 3 is appropriate.

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?

Specific verb (converts) plus resource (geospatial file), with the full source format list (CSV, KML, GPX, GeoJSON, zipped Shapefile as base64) and the target formats (GeoJSON, KML, CSV), plus what it returns. It also names the siblings it is not (reproject_geojson, measure_geojson), so an agent can distinguish it without opening a schema.

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?

Explicitly routes a specific case away: "To reproject or measure features that are already GeoJSON use reproject_geojson or measure_geojson." That is real when-to-use-else guidance. It does not broader distinguish against transform_geojson or convert_coordinates, but the key boundary is stated.

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.

Resources