Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

safety_audit

Read-only

Query the safety audit log to review tool executions, blocked attempts, rate-limit violations, and preflight failures, with filters for action type and tool name.

Instructions

Query the safety audit log.

        Returns a record of all safety-relevant operations: tool executions,
        blocked attempts, rate-limit violations, and preflight failures.

        Args:
            action: Filter by action type.  Options: ``"executed"``,
                ``"blocked"``, ``"rate_limited"``, ``"auth_denied"``,
                ``"preflight_failed"``, ``"dry_run"``.  Omit for all.
            tool_name: Filter by MCP tool name (e.g. ``"send_gcode"``).
            limit: Maximum number of records to return (default 25, max 100).

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": "safety_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of records to return (default 25, max 100). Default: 25.
actionNoFilter by action type. Options: ``"executed"``, ``"blocked"``, ``"rate_limited"``, ``"auth_denied"``, ``"preflight_failed"``, ``"dry_run"``. Omit for all.
tool_nameNoFilter by MCP tool name (e.g. ``"send_gcode"``).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.5.1
    • addedInput schema / properties / action / description
      Added value: +"Filter by action type.  Options: ``\"executed\"``, ``\"blocked\"``, ``\"rate_limited\"``, ``\"auth_denied\"``, ``\"preflight_failed\"``, ``\"dry_run\"``.  Omit for all."
    • changedInput schema / properties / limit / description
      Previous value: -"Default: 25."New value: +"Maximum number of records to return (default 25, max 100). Default: 25."
    • addedInput schema / properties / tool_name / description
      Added value: +"Filter by MCP tool name (e.g. ``\"send_gcode\"``)."
  2. Changed4 schema fields changedv1.5.0
    • removedInput schema / properties / action / default
      Removed value: -null
    • removedInput schema / properties / limit / default
      Removed value: -25
    • addedInput schema / properties / limit / description
      Added value: +"Default: 25."
    • removedInput schema / properties / tool_name / default
      Removed value: -null
  3. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, destructiveHint false, and openWorldHint false, so the safety profile is covered. The description adds useful context about what the log contains (blocked attempts, rate-limit violations, preflight failures), but says nothing about ordering, retention window, or whether results are paginated beyond the limit cap.

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 the purpose, then a single sentence on return contents, then a compact Args block. The docstring scaffolding ("Args:", doubled backticks) is slightly noisy but every line carries 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 read-only, zero-required-parameter filter tool with no output schema, the description adequately covers what the records represent and how to narrow them. Missing only ordering/recency and pagination behavior, which keeps it short of a 5.

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 100% and the description restates the same text nearly verbatim, including the limit default/max and the action option list. It adds no format details (e.g. whether tool_name must match exactly or whether action filtering is combined with AND), so it meets but does not exceed the baseline.

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?

Opens with a specific verb and resource ("Query the safety audit log") and enumerates the record types returned (tool executions, blocked attempts, rate-limit violations, preflight failures), which distinguishes it from generic event tools. It does not, however, mention nearby siblings such as export_audit_log, verify_audit_integrity, or get_session_log, so the agent must infer the boundary itself.

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

Usage Guidelines2/5

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

There is no statement of when to use this instead of export_audit_log, verify_audit_integrity, recent_events, or get_interception_history. The only conditional guidance is per-parameter ("Omit for all"), which is filter semantics rather than tool selection.

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

Deploy Server

Other Tools