Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_agents_ask_supervisor

Escalate unclear requirements, priorities, or unauthorized decisions by asking a supervisor with 2–4 concrete options; receive an answer or human escalation while continuing independent work.

Instructions

Ask the chief about a doubt you can't resolve alone: unclear requirements, priorities, or a decision you are not authorized to make. Give 2 to 4 concrete options, your preferred one first. The chief answers or escalates it to the human. Don't wait idle: keep working on what doesn't depend on it. The answer comes back as a new run or an inbox message. Never re-ask a question that was already answered.

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": {
      "question": "<question>",
      "options": "<options>"
    },
    "name": "kernel_agents_ask_supervisor"
  }
}

Input Schema

NameRequiredDescriptionDefault
envNoWhen the question is about the environment being broken (DEV down, a missing credential): its key, e.g. `dev-e2e`. If that problem is already open you join it and nobody is asked again.
contextNoBackground the user needs to decide (meeting summary, trade-offs).
optionsYes2 to 4 options, your preferred one first.
subjectNoWhat the question is about, as a key: an issue and its part (`web#2653:a-b`), an MR, a ticket. Taken from the question text when omitted.
categoryNoThe kind of question, the same slug every time for the same kind (`approve-mr`, `closer-blocked`, `env-down`). Past decisions are matched within a category.
questionYesThe question, in one sentence.
meeting_idNoIf the question came out of a meeting, reference its id.
for_operatorNoOnly the operator can decide or do this (approve a risky MR, set something in an environment, a product decision): skip the chief.
__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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the async contract ('answer comes back as a new run or an inbox message'), the escalation path to a human, deduplication behavior for env problems ('you join it and nobody is asked again'), and the instruction not to block. It does not say what the immediate call returns (e.g. a question id) or whether the call itself is synchronous.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then usage rule, then the async behavior, then the anti-pattern. Every sentence carries distinct information and none is padding.

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?

For a 9-parameter tool with no output schema, the description covers the full lifecycle an agent needs: when to ask, how to phrase options, that the answer arrives asynchronously, that env problems dedupe, and that repeats are forbidden. Little an agent needs to call this correctly is missing.

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%, so the schema already documents env, subject, category, meeting_id, for_operator and option fields in detail. The description only restates the options rule ('2 to 4 concrete options, your preferred one first'), adding no meaning beyond the schema — baseline 3 applies.

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 ('Ask the chief') plus the exact class of doubt it covers: unclear requirements, priorities, or unauthorized decisions. An agent can tell this is the escalation path to a supervisor rather than a knowledge lookup, though it never names the sibling lookup tools (kernel_brain_ask, kernel_graph_ask) it is contrasted with.

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

Usage Guidelines4/5

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

Gives clear triggering conditions ('a doubt you can't resolve alone') and a negative rule ('Never re-ask a question that was already answered'), and the for_operator parameter carves out cases that skip the chief entirely. It stops short of explicitly routing the agent to alternative tools for factual lookups versus decision escalations.

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