Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_agents_resume

Resume an interrupted agent run from its last checkpoint when the kernel reports it as resumable, without repeating tool calls whose outcome was lost.

Instructions

Resume an interrupted agent run from its last checkpoint (native agents only). Use it on a run the kernel failed with 'resumable with kernel_agents_resume'. Tool calls whose outcome was lost are not repeated — the agent is told their result is unknown.

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": {
      "run_id": "<run_id>"
    },
    "name": "kernel_agents_resume"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idYesRun ID to resume

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it discloses that execution restarts from a checkpoint, that tool calls with lost outcomes are deliberately NOT repeated, and that the agent is told those results are unknown. That is the key non-obvious semantic an agent needs. It omits error behavior (e.g., what happens if the run has no checkpoint) and the response shape.

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?

Two short sentences, front-loaded with the action and mechanism, then the eligibility condition and the critical side-effect caveat. No redundant restatement of the name or title, and every clause carries information the agent could not infer.

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 single-parameter, annotation-free recovery tool with no output schema, the definition covers eligibility, mechanism, and the most important behavioral risk (lost tool-call outcomes). What remains uncovered is the return value and failure modes, a modest gap for a tool this simple.

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?

Only one parameter and schema description coverage is 100%, so the schema already defines run_id. The description adds the useful qualifier that the run must be one that failed with the resumable marker, but nothing about ID format or lookup. Baseline 3 for a fully covered schema is appropriate.

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 ('Resume an interrupted agent run') plus the mechanism ('from its last checkpoint') and a scoping constraint ('native agents only'). An agent can immediately tell this is the recovery path for a failed run, distinct from creation or listing tools in the sibling set.

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 an explicit trigger: use it on a run the kernel marked 'resumable with kernel_agents_resume', which is a concrete, checkable condition rather than implied usage. It also restricts to native agents. It does not state what to do when a run is not resumable, which keeps it short of a full when/when-not pair.

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