Skip to main content

Token Optimization and Analytics

Token Optimization and Analytics helps admins understand where token usage comes from and reduce unnecessary cost or context.

Both surfaces live on the same page, Monitor > Tokens, which is titled Token Optimization. It has three views:

ViewWhat it does
AnalyzeShows token usage over a date range: conversation spend, response tokens, init context tokens, tool token usage, toolkit context savings, biggest spenders, and models used.
OptimizeLists recommended actions with estimated monthly savings, plus MCP context, toolkit context, skill size, and tool response opportunities. The Output Format control sits here.
DevicesBreaks usage down by the devices reporting to your organization.

Use Analyze to find the largest sources of token usage. Use Optimize and its recommended actions to reduce them.

How the pieces fit together

AI agents consume tokens in several places:

SourceWhy it matters
MCP contextMCP servers expose tool descriptions and input schemas. Large servers can add a lot of initial context before the agent calls any tool.
Toolkit contextToolkits expose curated subsets of tools. Smaller, focused toolkits reduce the initial context shown to agents.
Skill contextSkills are loaded into every AI conversation. Oversized skills raise the baseline cost of every session.
Tool responsesTool outputs can be large. Response mappings and output-format settings reduce the number of tokens returned to the model.

The normal workflow is:

  1. Enable Token Usage Analytics.
  2. Review recommendations on the Optimize view of Monitor > Tokens.
  3. Inspect high-context MCP servers, toolkits, and skills.
  4. Create smaller toolkits, move long skill content into references, or tighten tool responses.
  5. Adjust the output format if tool responses are a major source of usage.

Pages in this section

On this page