How it works
A bounded parser evaluates supported arithmetic using reduced i128 rational numbers. Exact comparisons include the supplied absolute and relative tolerance. Unsupported exact operations, transcendental functions and rational overflow yield an explicitly inconclusive floating estimate, not a certified error bound.
Inputs and units
A scalar expression up to 512 characters, named numeric values, a claimed numeric value and optional tolerances. JSON numeric values and claims must stay inside the safe integer magnitude; precise large constants can be written in the expression string.
What the result contains
A consistent, inconsistent or undetermined result; exact rational value when available, computed estimate, error, tolerances, comparison mode, canonical digest and stated scope.
Example MCP call
{
"name": "check_arithmetic",
"arguments": {
"expression": "a+b",
"values": [
{
"name": "a",
"value": 0.1
},
{
"name": "b",
"value": 0.2
}
],
"claimed_value": 0.3
}
}Send this tool name and arguments through a connected MCP client. Discover the authoritative input schema with tools/list.
Direct MCP access
check_arithmetic is independently callable. Its generated registration deliberately disables orchestration: no planner binding or approved adapter is supplied. Do not infer composability from matching JSON fields.
Execution and availability
ScoreCompute exposes this tool through MCP Streamable HTTP. Rust computation runs on a connected worker; the public website and MCP gateway run separately. Among these 19 scientific tools, CUDA is implemented for simulate_pi; the other engines currently run on CPU. The separate contributor pilot has its own fixed integer Monte Carlo workload. Requests are bounded and concurrent work may be refused when capacity is occupied.
Record inputs, assumptions and returned provenance when sharing a result. The public observatory displays software client names and tool activity, without publishing calculation arguments or results.