Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_agents_update

Update an existing agent definition, including its name, model, prompt, tools, limits, and active status, so the agent runs with current configuration and permissions.

Instructions

Update an agent definition (name, prompt, tools, config, active status)

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_agents_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesAgent ID
nameNo
modelNo
activeNo
providerNo
timeout_msNo
descriptionNo
denied_toolsNo
allowed_toolsNo
goal_templateNo
system_promptNo
max_iterationsNo
__caller_agent_idNo[internal] injected by the agent executor when this tool is invoked from an agent run. Not meant to be set by external callers.
show_on_dashboardNoShow last flow result as a widget on dashboard home

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

B3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden, yet it discloses almost nothing: it does not say whether this is a partial patch (omitted fields preserved) or a full replacement (omitted fields cleared), whether it affects currently running agent runs, what permissions are required, or whether changes are reversible. The only behavioral hint is the word 'Update', which is already inferable from the name.

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?

A single short parenthetical phrase with no filler and the verb/resource front-loaded. It is efficient, though its brevity comes at the cost of the information the other dimensions penalize, so it is concise rather than padded.

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?

For a 14-parameter mutation tool with no annotations, no output schema, and low schema coverage, the description is substantially under-specified. An agent could invoke it correctly only for the simple name/active cases and would be guessing on partial-update semantics for the remaining fields.

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 only 21% (14 parameters, essentially only id, __caller_agent_id, and show_on_dashboard documented), so the description must compensate and does not. Its parenthetical mentions 'prompt', 'tools', and 'config', which do not match the actual properties (system_prompt, goal_template, allowed_tools, denied_tools) and leave model, provider, timeout_ms, max_iterations, description, and show_on_dashboard entirely unexplained.

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?

States a specific verb and resource ('Update an agent definition') and lists the kinds of fields affected, which is enough to distinguish it from kernel_agents_create or kernel_agents_delete. However, the field labels ('prompt', 'tools', 'config') are generic and do not map cleanly onto the actual schema properties.

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?

Use is implied by the name and verb: mutate an existing agent identified by the required id. There is no explicit guidance on when to use this versus creating a new agent, versus configuring triggers/flows/decision policy through the many sibling tools, and no stated prerequisites such as the agent existing or being stopped.

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