Skip to main content
Glama

Read the audit log

get_audit_log
Read-only

Read the latest apply_plan audit log entries, newest first, to verify what each sync step created, updated, skipped, or failed. Filter by plan, outcome, or resource type and cap results with a limit.

Instructions

Read what apply_plan wrote: the most recent audit log entries, newest first, one per step (plan, target store, resource type, key, outcome and message). Filter by plan, outcome (created, updated, skipped, failed) or resource type. Returns { log (file path), matched, returned, entries }: limit (default 50) caps the entries while matched counts every match; in a very large log only the most recent 8 MB is searched. Use it after an apply to see exactly what was written; use apply_status for the progress of a running apply and get_plan for what a plan intended. The log is a local file; nothing is read from Shopify.

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": "get_audit_log"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax entries returned (default 50). matched counts them all.
outcomeNoOnly entries with this outcome.
plan_idNoOnly entries of this plan.
resourceNoOnly entries of this resource type.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.11.5

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint=false, and the description reinforces the closed-world claim ('The log is a local file; nothing is read from Shopify'). It adds genuine behavioral detail annotations cannot carry: newest-first ordering, the 8 MB search cap on very large logs, and the limit-vs-matched distinction, which prevents an agent from assuming pagination. It does not state what happens when the log file is absent or how truncation at 8 MB is signalled, so it stops short of full transparency.

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 filters, then return shape, then routing. Every clause carries information, but the middle sentence chain runs long and blends return-value detail with parameter restatement, which slightly dilutes scanability for an agent skimming for the routing sentence.

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?

There is no output schema, yet the description supplies the return shape ('{ log (file path), matched, returned, entries }') and explains the semantics of matched versus returned. Combined with the filter list, the 8 MB caveat, and sibling routing, an agent has everything needed to call this correctly on the first attempt.

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 coverage is 100% and both enum parameters are fully documented in the schema, so the baseline is 3. The description restates the same facts — 'limit (default 50)' and the outcome values 'created, updated, skipped, failed' — without adding syntax, interaction rules, or edge-case behavior beyond what the schema already states.

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 what apply_plan wrote: the most recent audit log entries') and pins down the unit of content ('one per step (plan, target store, resource type, key, outcome and message)'). An agent can distinguish this from get_plan and apply_status purely from this sentence, and the ordering ('newest first') is stated up front.

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 routing instructions: 'Use it after an apply to see exactly what was written; use apply_status for the progress of a running apply and get_plan for what a plan intended.' Both alternatives are named along with the condition that selects each, and the temporal trigger ('after an apply') is stated.

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