Skip to main content
Glama

Audit log (accountability trail)

audit_log
Read-only

Retrieve recent data-operation records showing who performed what action and when, with optional filtering by user ID; records remain available even after memory erasure.

Instructions

The accountability trail (GDPR Art. 5(2)) — recent data operations: who / what / when. Optionally filter by user_id. Not affected by memory erasure.

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
limitNo
user_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one genuinely valuable behavioral fact — that the trail is unaffected by memory erasure — but leaves 'recent' undefined (no time window) and says nothing about the default cap of 50 or pagination behavior.

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 tight sentences with the core identity front-loaded and the erasure caveat as a short trailing qualifier. No filler, though the em-dash parenthetical carries a compliance citation that may not help an agent select the tool.

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

Completeness3/5

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

An output schema exists, so return-value explanation is rightly omitted, and the read-only annotation covers safety. Still, for a query tool with an undocumented limit and an undefined 'recent' window, an agent lacks enough to predict result size or recency scope before calling.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must carry the burden for both parameters. It only mentions user_id as an optional filter and never explains whether that means actor, subject, or target, and it completely ignores limit, whose default of 50 and upper bound are documented nowhere.

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

Purpose4/5

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

The description gives a specific verb+resource framing: it returns 'recent data operations: who / what / when' as an 'accountability trail'. That is concrete enough to distinguish it from sibling tools such as verify_audit or attest, though it never names those siblings to make the distinction explicit.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the GDPR Art. 5(2) reference signals the accountability/compliance scenario, and 'Not affected by memory erasure' usefully tells an agent the log survives forget/purge. However, there is no explicit when-to-use versus when-not guidance and no named alternative for verification-style questions.

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