Token Optimization and Analytics
Token Optimization and Analytics helps admins understand where token usage comes from and reduce unnecessary cost or context.
Willow has two related product surfaces:
| Surface | Where it lives | What it does |
|---|---|---|
| Token Usage Analytics | Monitor > Tokens | Shows token usage, context footprint, recommendations, MCP context, toolkit context, skill size, and tool response optimization opportunities. |
| Token Optimization | Admin > Settings | Controls the tool output format Willow sends to the model, such as Default, JSON Compact, CSV, YAML, or TOON. |
Use Token Usage Analytics to find the largest sources of token usage. Use Token Optimization settings and the recommended actions to reduce them.
How the pieces fit together
AI agents consume tokens in several places:
| Source | Why it matters |
|---|---|
| MCP context | MCP servers expose tool descriptions and input schemas. Large servers can add a lot of initial context before the agent calls any tool. |
| Toolkit context | Toolkits expose curated subsets of tools. Smaller, focused toolkits reduce the initial context shown to agents. |
| Skill context | Skills are loaded into every AI conversation. Oversized skills raise the baseline cost of every session. |
| Tool responses | Tool outputs can be large. Response mappings and output-format settings reduce the number of tokens returned to the model. |
The normal workflow is:
- Enable Token Usage Analytics.
- Review recommendations in Monitor > Tokens.
- Inspect high-context MCP servers, toolkits, and skills.
- Create smaller toolkits, move long skill content into references, or tighten tool responses.
- Adjust output-format settings if tool responses are a major source of usage.
Pages in this section
- Enable Token Usage Analytics - turn on the beta analytics feature in Settings.
- Review Token Usage - read the Tokens dashboard and recommended actions.
- MCP Context - find MCP servers with large tool-description and schema footprint.
- Toolkit Context - use toolkits to reduce initial context.
- Skill Token Analysis - identify oversized skills and extract references.
- Tool Response Optimization - find unmapped high-token tool responses.
- Output Format Optimization - configure Default, JSON, CSV, YAML, or TOON output formats.