Skip to main content
Glama

Read audit log

read_audit
Read-only

Read recent audit-log rows newest first to review what jobs ran and how they ended; filter by session, operation, outcome, request_id, or time, and verify the hash chain.

Instructions

Read recent audit-log rows, newest first: what each job was asked and returned. Filter by session_id, operation, outcome, request_id, since_unix (seconds); verify=true checks the hash chain. Use when: you review what ran and how it ended, or look one job up by request_id. Avoid when: you want live metrics (health). Output: rows[] {session_id, operation, outcome, reason_code, reason, args_hash, command, request_id, started_at_ms, completed_at_ms, elapsed_ms, args_summary, result_summary, result_bytes}, count, truncated, chain_ok (verify=true). Output mode full adds redacted args and result per row; bulk text is kept as its length only. Timestamps are epoch milliseconds (since_unix filters in seconds). args_hash identifies the call, command is the redacted command line.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "read_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax rows, newest first (default 50; 15 in VENIRA_OUTPUT_MODE=compact; max 200).
verifyNotrue verifies the audit hash chain and returns chain_ok; false disables verification.
outcomeNoOnly rows with this outcome.
operationNoOnly rows for this operation (e.g. edit_file, shell_run).
request_idNoOne job by request_id: its args and result.
session_idNoOnly rows from this session.
since_unixNoOnly rows at or after this Unix timestamp (seconds).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv4.5.0
    • removedInput schema / properties / verify / anyOf
      Removed value: -[
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "maximum": 1,
      -    "minimum": 0,
      -    "type": "integer"
      -  }
      -]
    • changedInput schema / properties / verify / description
      Previous value: -"1 verifies the audit hash chain and returns chain_ok; 0 disables verification."New value: +"true verifies the audit hash chain and returns chain_ok; false disables verification."
    • removedInput schema / properties / verify / maximum
      Removed value: -1
    • removedInput schema / properties / verify / minimum
      Removed value: -0
    • changedInput schema / properties / verify / type
      Previous value: -"integer"New value: +"boolean"
  2. Addedv4.0.0

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and a closed-world scope, and the description still adds real substance: hash-chain verification via verify=true, newest-first ordering, the compact-mode row cap interaction, and the full-mode caveat that bulk text is reduced to a length. It stops short of stating pagination or cost behavior, but for a read tool this is well beyond the annotation floor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then a compact Use/Avoid block, then output shape — a sensible triage order. The output field list is long but justified because no output schema exists; slight redundancy in restating filter names that the schema already documents.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With seven optional parameters and no output schema, the description carries the return-value burden itself by enumerating rows[], count, truncated, chain_ok and the full-mode delta. Nothing an agent needs to call this correctly or interpret the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns above that by flagging the unit mismatch ('since_unix filters in seconds' while timestamps are epoch milliseconds) and restating verify's chain-check semantics. That clarification prevents a real class of invocation error the schema alone doesn't surface.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read recent audit-log rows'), adds ordering ('newest first') and content ('what each job was asked and returned'). This clearly separates it from siblings like git_log or health, which cover history of commits and live metrics respectively.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit 'Use when' covers both a review pass and a single-job lookup by request_id, and 'Avoid when: you want live metrics (health)' names the alternative tool and the condition that selects it. An agent needs no inference to route correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.