Skip to main content
Glama

Audit log

audit_log
Read-onlyIdempotent

Read the MCP audit trail to see which session ran a command or edited a file, when, and with what exit code. Use it first when something breaks or a file changes unexpectedly.

Instructions

Read the MCP audit trail: who (which session) ran which command or edited which file, when, and with what exit code. USE THIS FIRST when something broke, when a file looks unexpectedly changed, or when you suspect another agent worked in parallel. Filters: onlyErrors, tool, contains, sinceMinutes.

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": "audit_log"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoShort human-readable explanation (1 line, in the user's language) of what you are about to do and why. Shown to the user on the approval card. Always provide when calling mutating tools.
toolNo
agentNoShort consistent identifier or display name of this agent (e.g. 'Claude · Лендинг', 'Тесты', 'Мой агент'). Used to separate tasks and route tray messages when multiple agents work in parallel.
limitNo
containsNo
onlyErrorsNo
sinceMinutesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already state readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the agent knows this is a safe repeatable read. The description adds genuinely new context by enumerating what each audit entry contains, which annotations cannot express. However, it says nothing about retention, pagination, output size caps or how far back the trail goes, which matters for a log-reading tool.

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?

Two sentences with the primary use case front-loaded and capitalized for emphasis, followed by a compact filter list. No filler; the only minor inefficiency is that the filter sentence repeats parameter names without adding information.

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

Completeness4/5

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

For a zero-required-param read-only tool with a rich annotation set and no output schema, the description covers purpose, triggers and the filter surface adequately. The main gap is operational: limit/pagination behavior and any time-window defaults go unstated, so an agent cannot predict result size.

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

Parameters3/5

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

Schema description coverage is only 29%, so the description must compensate, and it does so only partly. It names four filters (onlyErrors, tool, contains, sinceMinutes) and frames them as filters, but adds no meaning: no default or unit for sinceMinutes, no statement of whether contains is a substring or regex match, no matching semantics for tool. The remaining params (limit, agent, note) are covered by the schema, not the description.

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?

A specific verb and resource: "Read the MCP audit trail", immediately narrowed to the recorded fields (session, command, file, timestamp, exit code). That level of detail lets an agent distinguish it from journal_log or task_status without opening any schema.

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

Usage Guidelines4/5

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

Explicit trigger conditions are given: "USE THIS FIRST when something broke, when a file looks unexpectedly changed, or when you suspect another agent worked in parallel." That is clear when-to-use guidance, but there are no exclusions or named alternatives for the case where journal_log or task_status would be the better pick.

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