> ## Documentation Index
> Fetch the complete documentation index at: https://docs.interchange.io/llms.txt
> Use this file to discover all available pages before exploring further.

# v3 Limits

> Design v3 clients for bounded tool calls, connection lifetime, payload limits, and upstream latency.

v3 shares the platform's transport protections and adds preview-specific
operational bounds:

* one MCP connection remains open for at most 30 minutes;
* one tool call is limited to 30 minutes;
* deploys may interrupt long in-flight work after the drain window;
* structured responses over 200 KB are truncated as a safety backstop; and
* `request_proposals` waits at most 30 seconds per seller and reports bounded
  per-seller outcomes.

Use returned cursors, keep pages small, and preserve partial results. A retry
must reuse an idempotency key only when it represents the same logical attempt.
Upstream seller and inventory systems can dominate latency even when the v3
facade itself is healthy.

<Card title="Full rate-limit reference" icon="book" href="/v2/reference/rate-limits">
  Review the canonical HTTP and MCP rate-limit behavior and retry guidance.
</Card>