Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_audit_who_changed

Trace which agent, run, or MCP client wrote or returned a given id—showing the tool used, timestamp, success status, and arguments so you can see who changed it.

Instructions

Who changed this? Every tool call that wrote and named or returned this id (a task, contact, note, fact…): the agent and run or the MCP client that made it, the tool, when, whether it worked, and its arguments in short.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

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

Input Schema

NameRequiredDescriptionDefault
idYes
limitNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose what the audit surfaces: the agent and run or MCP client, the tool, the timestamp, whether the call succeeded, and a short argument summary. It also discloses the matching semantics (wrote AND named/returned the id), which is real behavioral value. It does not state that the operation is read-only, nor how much history is scanned or how results are capped, which matters for an unbounded-looking lookup.

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 motivating question, then a single dense sentence enumerating exactly what comes back. Nothing is padded, though the second half is a long run-on list that could be broken for faster scanning.

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?

An output schema exists, so the description needn't spell out return shape, and it still usefully previews the fields. For a 2-parameter lookup this is nearly sufficient; the remaining gap is the unmentioned limit/truncation behavior and the scope of the history being scanned.

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 0%, so the description must compensate. It does well on `id`, explaining that it may be a task, contact, note, or fact id and that matching covers both writes naming the id and returns containing it. The `limit` parameter (default 30) is never mentioned, so the agent gets no signal that results are truncated or how to page through more than 30 hits.

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 names a specific question ('Who changed this?') and precisely defines the search: every tool call that wrote and named or returned this id, with examples of id types (task, contact, note, fact). That is far more concrete than a restatement of the name. It stops short of contrasting itself with the sibling kernel_audit_changes, so the boundary between the two audit tools is left to inference.

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?

The opening question implies the use case (provenance/attribution for a specific record) and the body clarifies the matching rule, which is a form of usage context. However, there is no explicit when-not guidance, no named alternative such as kernel_audit_changes, and no statement about cost or scope of the scan that would help an agent choose between audit tools.

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