--- title: What to Log When an Agent Calls a Tool: AI Agent Audit... description: AI agent tool calls need a dedicated audit trail rather than relying on chat history, which only captures user requests, not the actual tool invoked, arguments... canonical: https://daily.dev/posts/what-to-log-when-an-agent-calls-a-tool-ai-agent-audit-trail-schema-zxc7p3ojj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: What to Log When an Agent Calls a Tool: AI Agent Audit Trail Schema | daily.dev og:description: AI agent tool calls need a dedicated audit trail rather than relying on chat history, which only captures user requests, not the actual tool invoked, arguments... og:url: https://daily.dev/posts/what-to-log-when-an-agent-calls-a-tool-ai-agent-audit-trail-schema-zxc7p3ojj og:image: https://api.daily.dev/og/posts/ZxC7p3OjJ.png og:image:alt: What to Log When an Agent Calls a Tool: AI Agent Audit Trail Schema og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # What to Log When an Agent Calls a Tool: AI Agent Audit Trail Schema **[Obot AI](https://daily.dev/sources/obotai)** · [@obot_ai](https://daily.dev/obot_ai) · 1 min read · 0 upvotes · 0 comments ## Summary AI agent tool calls need a dedicated audit trail rather than relying on chat history, which only captures user requests, not the actual tool invoked, arguments passed, results returned, latency, or policy decisions. A practical logging schema is proposed covering these fields, along with guidance on where to store the records and retention periods. The piece also argues that logging at the gateway layer (like Obot) is generally preferable to embedding logging logic inside each individual MCP server. ## Content _By Stein Ove Helset, _[_Obot AI_](https://obot.ai/?utm_source=devto&utm_medium=syndication&utm_campaign=ai-agent-audit-trail-schema) 📓 [Read the full article](https://obot.ai/blog/what-to-log-when-an-agent-calls-a-tool-ai-agent-audit-trail-schema/?utm_source=dailydev&utm_medium=syndication&utm_campaign=ai-agent-audit-trail-schema) -------------------------------- At some point if you're running AI agents, something in your system changes and you have no idea if it was the agent, a person, or something else. You go back to check — and all you have is the chat history. _But Chat history isn't an audit trail._ It tells you what the user asked for. It doesn't tell you which tool was called, with what arguments, what came back, how long it took, or what policy decision let it through. When something goes wrong — or an auditor asks — that's the record you actually need. This post is a practical guide to what to log for every AI agent tool call: a full schema you can copy (with field-by-field explanation of why each one matters), where to store it, and how long to keep it. It also covers why the gateway layer like Obot is usually a better place to write these records than inside each MCP server individually. 📓 [Read the full article](https://obot.ai/blog/what-to-log-when-an-agent-calls-a-tool-ai-agent-audit-trail-schema/?utm_source=dailydev&utm_medium=syndication&utm_campaign=ai-agent-audit-trail-schema) ## Similar posts on daily.dev - [What your logs can’t tell you when an AI agent acts alone](https://daily.dev/posts/what-your-logs-can-t-tell-you-when-an-ai-agent-acts-alone-mu2wtboeu) · The New Stack · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#logging](https://daily.dev/tags/logging), [#observability](https://daily.dev/tags/observability), [#mcp](https://daily.dev/tags/mcp) [View this post on daily.dev](https://daily.dev/posts/what-to-log-when-an-agent-calls-a-tool-ai-agent-audit-trail-schema-zxc7p3ojj) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/what-to-log-when-an-agent-calls-a-tool-ai-agent-audit-trail-schema-zxc7p3ojj","headline":"What to Log When an Agent Calls a Tool: AI Agent Audit Trail Schema","text":"AI agent tool calls need a dedicated audit trail rather than relying on chat history, which only captures user requests, not the actual tool invoked, arguments passed, results returned, latency, or policy decisions. A practical logging schema is proposed covering these fields, along with guidance on where to store the records and retention periods. The piece also argues that logging at the gateway layer (like Obot) is generally preferable to embedding logging logic inside each individual MCP server.","url":"https://daily.dev/posts/what-to-log-when-an-agent-calls-a-tool-ai-agent-audit-trail-schema-zxc7p3ojj","datePublished":"2026-09-01T20:22:59.104Z","dateModified":"2026-09-01T20:23:19.998Z","author":{"@type":"Person","name":"Obot AI","url":"https://daily.dev/obot_ai","image":"https://media.daily.dev/image/upload/s--uppa7UXU--/f_auto/v1779993498/avatars/avatar_SnPRm3tML5D33cwMQ1w5q?_a=BAMAMiWQ0","description":"Open-source AI Control Plane","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":90}},"image":"https://media.daily.dev/image/upload/s--IQAt224d--/f_auto/v1788294180/posts/ZxC7p3OjJ?_a=BAMAMicg0","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"isPartOf":{"@type":"WebPage","url":"https://daily.dev/squads/obotai","name":"Obot AI"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Obot AI","item":"https://daily.dev/squads/obotai"},{"@type":"ListItem","position":3,"name":"What to Log When an Agent Calls a Tool: AI Agent Audit Trail Schema"}]} ```