Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_plan_validate

Validate and simulate a DAG plan without executing it: detect cycles, dangling dependencies, and unknown tools, then estimate cost and latency and flag side effects requiring approval.

Instructions

Validate + simulate a plan (DAG of tool calls). Pure: nothing executes. Returns issues (cycles, dangling deps, unknown tools), estimated_cost (sum of per-node p50s, latency = critical path), side_effects_preview, and requires_approval (true when any node calls a non-reversible tool). Pair with kernel_plan_execute.

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": {
      "plan": "<plan>"
    },
    "name": "kernel_plan_validate"
  }
}

Input Schema

NameRequiredDescriptionDefault
planYes

Output Schema

NameRequiredDescriptionDefault

No arguments

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 supplied, the description carries the full disclosure burden and does well: it declares the operation is pure/side-effect-free, enumerates the issue classes detected (cycles, dangling deps, unknown tools), and explains the cost/latency model (sum of per-node p50s, latency = critical path). It omits any note on auth, size limits, or how long validation takes, which keeps it from a 5.

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?

Dense and front-loaded: purpose first, then purity guarantee, then return contract, then the sibling pairing. No filler sentences, and each clause delivers a distinct fact.

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's return-value summary is a bonus rather than a necessity, and the purity/approval semantics cover the risky parts. The remaining gap is the plan input structure, which is complex and entirely undocumented in both description and schema.

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 0% and the single `plan` parameter is a deeply nested object with undocumented fields (on_error, args_from, args_template, depends_on, and the constraints block with max_usd/max_latency_ms). The description mentions nodes and tool calls in passing but adds no meaning about these fields, leaving the agent to infer semantics from bare property names.

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 pair (validate + simulate) and resource (a plan, defined as a DAG of tool calls), and immediately distinguishes itself from the executor with 'Pure: nothing executes' and 'Pair with `kernel_plan_execute`.' An agent can tell exactly what this does versus its closest sibling.

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?

The pairing instruction with `kernel_plan_execute` implies the validate-then-execute workflow, and 'requires_approval (true when any node calls a non-reversible tool)' signals the gating use case. There is no explicit 'do not use this for X' exclusion, but the context is clear enough to place the tool correctly.

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