Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_kernl_bug_report

File a bug report against Kernl's code or behavior when a failure is caused by Kernl itself, including wrong results, missing events, crashes, or tools that do not work as described.

Instructions

Chief only. File a bug in Kernl itself — its code or behaviour — for Kernl's developers. Use it when a failure is Kernl's fault: a wrong result, a missing event, a crash, a tool that does not do what it says. Do NOT use it for an agent hitting its limits (steps, tokens, time), a provider outage or rate limit, expired auth, or an agent's prompt: those are fixed by the operator, not by changing Kernl. Give a precise title, the area of Kernl you believe is at fault, and your diagnosis with evidence. The report stays local until the operator publishes it.

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": {
      "title": "<title>",
      "area": "<area>",
      "diagnosis": "<diagnosis>"
    },
    "name": "kernel_kernl_bug_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaYesWhere in Kernl it lives, e.g. 'executor/claude-code', 'agents/api', 'dashboard/3d'.
reproNoHow to reproduce, markdown.
titleYesOne line naming the bug, e.g. 'agents.stop never emits run_completed'.
run_idNoThe failed run that showed it.
diagnosisYesRoot cause and evidence, markdown.
__caller_agent_idNo[internal] injected by the agent executor.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral load and does well: it discloses the 'Chief only' permission gate and that 'the report stays local until the operator publishes it', which is a non-obvious lifecycle fact an agent could otherwise get wrong. It stops short of saying what is returned (an id, a queued status) or whether duplicates are detected against kernel_kernl_bugs_list.

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 access constraint then the action, followed by use/do-not-use blocks and a closing lifecycle note. Every sentence does distinct work and there is no restatement of the name or title.

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 six-parameter mutation tool with no output schema and no annotations, the description covers who may call it, when, what to supply, and where the report goes. The remaining gaps are the return value and any interaction with kernel_kernl_bugs_list, which are minor.

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 all six parameters including repro, run_id and __caller_agent_id are already documented in the schema; that sets the baseline at 3. The description adds quality guidance ('precise title', 'area of Kernl you believe is at fault', 'diagnosis with evidence') but names only three of the fields, leaving repro and run_id entirely to the schema.

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 ('File a bug in Kernl itself — its code or behaviour') plus the audience ('for Kernl's developers') and an access constraint ('Chief only'). The exclusion list separates it from the agent-facing report tools in the sibling set, so an agent can pick it without opening a schema.

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?

Gives explicit positive triggers (wrong result, missing event, crash, tool not matching its description) and explicit negative triggers (agent step/token/time limits, provider outage or rate limit, expired auth, agent prompt), with the reason why each negative case belongs elsewhere. This is the strongest form of routing guidance.

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