OMP injects `INTENT_FIELD` (`i`) into every tool's wire schema. The direct
model tool-call path strips it via `extractIntent` in agent-loop, but the
eval `tool.*` bridge forwards args verbatim, so strict-schema MCP servers
(Linear, anything with `additionalProperties:false` / Zod `.strict()`)
rejected every call with `-32602 unrecognized_keys: ["i"]`. The eval
bridge surfaced the rejection as `hasError: true` instead of throwing, so
batch callers reading the value as success silently mutated nothing.
Move the strip to the MCP boundary so it owns the contract regardless of
caller: `MCPTool.execute` / `DeferredMCPTool.execute` route params through
a new `prepareOutboundArgs` that runs `stripHarnessIntent` before
`omitUnusedOptionalArgs`. `stripHarnessIntent` leaves `i` in place when
the server's own `inputSchema.properties` declares it, so a server that
legitimately uses `i` as a parameter is unaffected.
Fixes#3575
Pruned empty optional MCP argument placeholders before tools/call while preserving required fields and meaningful falsy values.
Added regression coverage for active and deferred MCP tools.
Fixes#3302
can1357